anthony-chaudhary
UserCatch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
Categories
Indexed Skills (83)
issue-verify
Adjudicate a GitHub issue's "this is resolved" claim from witnesses the claimant didn't author — then close it carrying the evidence, or refuse with the typed gap. Use when an issue looks already-solved, after landing a fix that should have closed one, or to sweep open issues for silently-resolved ones.
issue-work
Pick the next most important open GitHub issue this agent can actually complete, make its done-condition true, land it with witnesses (suite + parity + commit-audit), and priority-tag every issue touched along the way. Use when asked to "work the backlog", "complete the next most important issue", or to fix a specific issue number end-to-end.
stable-release
Promote an already-shipped rolling release (vX.Y.Z) of the DOS kernel to a named stable channel — gated on a green kernel suite + a green third-party CI run on the candidate + a clean truth syscall + a soak window. Writes an evidence file and adds a stable/<codename> git tag on the same commit. Does NOT bump versions or build new artifacts.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commit-audit` — never the agent's own narration.
release
Cut a versioned release of the DOS kernel — bump the version, draft release notes, commit, tag, push to master, and create a GitHub release. The tag push triggers the gated PyPI publish pipeline (publish.yml); the skill surfaces the run and its approval gate.
dos-dispatch-loop
Run recurring `dos-dispatch` cycles, switching to `dos-replan` when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.
dos-plan-price
Price a proposed multi-agent fan-out before launching workers. Use when a packet, goal fleet, or hand-written plan would run several agents over declared file trees and you need DOS to catch collisions before any...
dos-replan
Refresh a plan portfolio from evidence: close shipped queue items, update cooldown state, and surface the few decisions an operator must make. Use after dispatch bursts, drained backlogs, or recurring findings.
dos-witness-claim
Verify subagent or worker results before folding them into a synthesis. Use when another agent claims it shipped, created, found, or changed something and your next step would otherwise trust its return string.
dos-class-cycle
Run one DOS plan-class lifecycle tick from the workspace `[lifecycle]` table: evaluate declared transitions, have a judge approve/defer them, write gated plan-meta edits, and log the cycle. Use when gardening plan lifecycle classes automatically.
dos-enforce-tune
Tune DOS enforcement policy knobs (`[intervention_policy]`, `[intervention]`, `[improve]`) from false-deny versus held-catch evidence. Use when running `dos enforce-tune` to keep only measured net_task_delta gains and escalate repeated non-keeps.
dos-goal-fleet
Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and `dos arbitrate` file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.
dos-goal-gate
Ground a keep-working goal in evidence the worker did not author by wiring `dos hook stop` to refuse false done claims. Use for one self-stopping agent or loop worker; use `dos-witness-claim` for fold barriers.
dos-promote
Surface units held out of the pickable set with their typed HoldReason and derived unblock action, auto-applying only safe reclassifies. Use when work is stuck unpickable and a human needs the exact unblock move.
dos-replan-loop
Run bounded, recurring `dos-replan` sweeps, optionally guarded by the workspace's release policy. Use when the planning queue needs unattended refresh for a fixed cadence rather than one manual sweep.
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use `dos-enforce-tune` for policy knobs.
dos-setup
Confirm the DOS plugin is wired: check the `dos-kernel[mcp]` package import, run `dos doctor`, show the bundled hooks/MCP/skills, and point to the next skill. Use after install or when plugin MCP/hooks fail.
dos-skillify
Convert an agent skill into a DOS-grounded variant by replacing self-certified claims with `dos` witness checks and emitting an additive copy plus report. Use when asked to make a skill DOS-aware or audit its self-checks.
dos-stats
Fold the plugin hook observation log into counts, reason classes, stop-blocks, wait-marker budget, and latency. Use to confirm the bundled native hook path is active or to inspect DOS hook activity; read-only.
dos-supervise-loop
Keep a target count of dispatch loops alive across the workspace lane roster: spawn missing loops, scavenge stalled leases, and surface spinning workers. Use when supervising a DOS dispatch-loop fleet.
dos-unstick
Analyze BLOCKED/DRAIN run history, cluster recurring causes, and propose one structural fix per wedge via `dos decisions`. Use when a fleet keeps stalling and you want a systemic unblock rather than another manual nudge.
dos-dispatch-loop
Run recurring `dos-dispatch` cycles, switching to `dos-replan` when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.
dos-dispatch
Plan and ship the next batch on one lane: run `dos-next-up`, acquire a lease with `dos arbitrate`, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
dos-next-up
Snapshot the repo's phased-plan portfolio into a dispatch packet: audit candidates with `dos verify`, render who-does-what, and emit a `dos gate` verdict. Use when you need the current next-work view before dispatching agents.
dos-plan-price
Price a proposed multi-agent fan-out before launch by computing tree collisions, safe concurrency, and a cheaper disjoint partition. Use before `dos-goal-fleet`, a `dos-next-up` dispatch packet, or any N-agent tree split.
dos-replan
Refresh a plan portfolio from evidence: close shipped queue items, update cooldown state, and surface the few decisions an operator must make. Use after dispatch bursts, drained backlogs, or recurring findings.
dos-witness-claim
Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.
commit-clean
Commit finished work cleanly on the shared trunk — lint the subject with `fak commit --preview`, then stage-and-commit EXACTLY your paths in one locked step via `fak commit --path … -m "…"`, verify the landed...
issue-triage
One repeatable pass over the open GitHub issue backlog — classify every open issue (needs-priority / needs-kind / needs-area, orphaned P0-P1, stale, dormant question), rank them into a deterministic "do next" order,...
memory-compact
Compact and structure a Claude Code auto-memory store so MEMORY.md stays under the harness load cap (first 200 lines / 25KB load each session — content past that SILENTLY never loads) while every memory stays...
negframe-score
One repeatable pass that keeps agent-steer prose leading with the AFFORDANCE, not the prohibition. Runs `fak score negframe` over the steer-prose corpus (AGENTS.md, CLAUDE.md, the skills, or explicit paths), reads...
operator-heaviness-score
One repeatable pass that keeps fak light to DRIVE — the operator-facing counterpart of steerability-score. Runs the operator-heaviness scorecard (`fak operator heaviness`) over the live operator surface (the cmd/fak...
phased-plan
Ceremony rules for shipping a phase of a phased plan — when to release, when to emit a handoff prompt, how far to go on type-strengthening, when to fold or split phases, and the hero-exit rule that prevents plans...
plan-audit
Reconcile every plan-state surface a project tracks into one completion audit — how many recent plan tasks shipped, how many remain, and which surfaces disagree. Runs the project's plan-audit helper and renders a...
skill-score
One repeatable pass that keeps the skill pack itself effective — the one surface no other scorecard grades. Runs the skill-effectiveness scorecard (`fak skill-effectiveness-scorecard`) over every...
slop-score
One repeatable RSI pass over CODE SLOP — the slop the compiler can't see. Runs the code-slop scorecard (tools/code_slop_scorecard.py), reads the slop-debt work-list, retires debt worst-first using ONLY genuine fixes...
bottleneck-map
Map the current "what is limiting us right now?" state across the running agent fleet and the live GitHub issue backlog. Runs fleet bottleneck detection plus issue triage, records the dominant system bottlenecks,...
milestone-score
One repeatable pass that makes the milestone report's CLIMB and ROADMAP retirable by the RSI loop — the milestone counterpart of quality-score (code) and stability-score (trust under iteration). Runs the milestone...
question-loop
The super-loop-family member that ASKS instead of ships. It launches detached workers whose only job is to ask 5–10 hard, honest questions about what the repo is doing — the question no other agent has asked, the...
run-it-all-night
Plan and run one bounded overnight issue worker through fak's guarded dispatch path, with typed capacity admission, lane leases, explicit dry-run/live gates, and independent git/DOS/test reconciliation. Use when the...
spine-fanout
Apply the two new-work defaults — ship the minimal WORKING end-to-end spine first (or file the spine as its own issue), then fan out the 3..50+ follow-on QA/dogfood/productization backlog at creation time via `fak...
stale-work-loop
Generated Codex adapter for the canonical fak project skill stale-work-loop.
stability-score
Generated Codex adapter for the canonical fak project skill stability-score.
agent-readiness
One repeatable pass that keeps fak the path of least resistance for an AI agent — Claude Code, OpenAI Codex, Cursor, an MCP client — to discover, adopt, and build on. Runs the agent-readiness scorecard (`fak score...
appeal-score
One repeatable pass that makes a doc read like a person wrote it, not a model. Runs the doc-appeal scorecard (tools/doc_appeal_scorecard.py), turns each HARD defect into a required edit (em-dash flood, bold-emphasis...
clean-skill
Audit a Claude Code skill's per-invocation context use, then propose a context-bundling helper + SKILL.md edits to cut waste. Reads a representative session JSONL, ranks the largest tool results, traces them back to...
conflation-score
One repeatable pass that keeps every number and status fak reports PROVENANCE-HONEST - each value labeled by what fak CONTROLS (witnessed/authored) vs what it only OBSERVES (relayed from an external party), and no...
disambiguation-score
One repeatable pass that keeps fak's growing namespace CRYSTAL-CLEAR - each similar-sounding concept (cache / vCache / KV cache / cachemeta / the provider prompt-cache; guard vs gate; the two witnesses) given one...
dojo-rsi-score
One repeatable pass that keeps the dojo's self-improving RSI loop actually CLOSING on our own billed usage - the real calibration history the dojo measures - instead of a plan-mode scaffold that never acts. Drives...
field-borrow
High-priority default "inspired by" workflow. Invoke proactively whenever an external product, repository, paper, standard, benchmark, release, issue, PR, roadmap, design discussion, or field practice could improve...
guard-rsi-score
One repeatable pass that keeps the RSI loop for `fak guard` actually CLOSING on our own usage - the real, hash-chained decision journal `fak guard` writes - instead of a plan-mode scaffold that never closes. Runs...
refresh-readme
One repeatable pass over README.md — the front door — that keeps ONLY the most important points current and honestly framed. Runs the freshness auditor (tools/readme_freshness_audit.py), turns each FAIL into a...
skill-lifecycle
Witnessed lifecycle for the project skill pack — usage-telemetry sidecar, value/idle-driven auto-archive (never delete, restorable), pin-exemption, journaled reversible transitions. Use to record skill usage, review...
skill-overlap
Flag content-redundant SKILL.md pairs as merge candidates — pairwise body cosine similarity over the skill pack, sorted highest-first. Use when the pack feels bloated or two skills seem to overlap, to find "skills A...
sota-check
One repeatable pass that stops fak from re-inventing known kernel art - before writing or optimizing a compute kernel (a quantized GEMM, a fused attention, a KV-cache reuse, a MoE dispatch, a Metal/CUDA kernel), it...
signal-first
Shape an answer for fast scanning with result-first sentences, concrete verbs, compact structure, and selectable compression while preserving every correctness-critical detail. Use when the user asks for...
disambiguate-section
Apply the concept-disambiguation pass to ANOTHER section of fak - an under-covered watched family (gateway-engine, guard-gate, ...) or a newly-discovered overloaded root (evict, decision, render, plan, pool, layout)...
harness-garden
Use when recent trajectories, notes, or refusals should become one evidence-backed harness improvement ticket and at most one guarded worker.
claim-repro-score
One repeatable RSI pass over claim reproducibility; run the claim-repro scorecard, retire unfalsifiable witness debt worst-first by adding the real artifact/test/path, re-measure, and commit only the claim-repro...
harness-creator
Create or customize a fak-native agent harness from a user's needs. Use when someone asks to make their own harness, agent product, branded/local UI, provider or tool profile, or a "10-minute" / "weekend" harness...
clear-out-wip
Clear backed-up local repository work without sweeping up peers - inventory the dirty tree, remove proven generated junk, prioritize coherent slices, ship green partial/enabling work honestly, park or issue the...
curate-cluster
Reconcile a research or documentation cluster's index with files on disk, repair dangling references, refresh counts and context, and ignore regenerable artifacts. Commit only quiescent documentation, experiment,...
industry-score
One repeatable pass that keeps fak's competitive story honest AND complete — graded industry-first, not from what fak happened to measure. Runs the industry scorecard (tools/industry_scorecard.py) over a modular...
lightgap-score
One repeatable pass that answers "is fak actually worth adopting, for whom, and what does it cost you to find out?" on an UNBOUNDED scale anchored at two ends — the next-best option a given buyer would really use,...
modularize
One focused, repeatable pass that retires the code-quality scorecard's `architecture` debt — the god-files (>1500 lines) and god-functions (>200 lines) that /quality-score flags as RISKY and explicitly defers to "a...
persona-score
One repeatable pass that keeps fak serving the top-10 personas who land on it — from the free-tier dev who downloads a binary and won't read a word, through the infra engineer who has to operate it, to the...
refresh-cachedoc-numbers
Refresh the recent-operational cachevalue numbers in a guarded doc (e.g. docs/integrations/fable5-more-usage-for-free.md) when this-week's telemetry has moved on. Re-derives the frozen snapshots from live `fak...
score-2x
The generic 2×-then-discover loop the scorecard family runs — enumerate exhaustive raw debt, drive it down 2× with genuine fixes, rescore to PROVE the drop, and continuously harden discovery under a new metric...
scorecard
The generic scoring doctrine the whole fak scorecard family instantiates — how to BUILD a new deterministic, tree-cross-checked, debt-driving scorecard and how to RUN any of them as a repeatable RSI pass. Every...
scout-loop
The super-loop that closes the research→backlog loop — it chains the outward CRAWLERS (the daily `idea-scout` arXiv/GitHub feed, the industry scans, the RESEARCH/CONCEPT corpus) into the STUDY pipeline...
resume-watchdog-audit
Audit and recover crashed Claude and Codex sessions through one dry-run-first cohort surface, with exact provider identity and post-launch transcript/thread advancement; then audit the scheduler tower that keeps...
cross-validate
Cross-validate code changes with independent subagents, execute on-device test witnesses, and generate GitHub issues for discovered follow-ons by default (DOS style). Use after implementing any fix or feature,...
debt-clean
One repeatable, evidence-backed pass that retires a bounded batch of maturity debt worst-first across the system's dedicated debt lanes. Features rich queryability (--query, --health), cross-indexes related items (dual-repo companions, tests, runtime-proofs, benchmarks, inbound blast radius), targets high-carrying-cost or degraded hotspots, advances maturity with tests, integration, and benchmarks, re-measures with --compare to prove the denominator was level-set, and commits by explicit path with (fak <leaf>). Use when cleaning or retiring maturity debt across units of work.
debt-orchestrator
Coordinate bounded, evidence-backed maturity debt work in the current repository, with isolated workers and independent verification. Use for debt burndowns or explicitly requested sustained campaigns.
git-subagent-sync
Synchronize subagent changes to git on shared trunk across all lanes and all untracked WIP by default (or scoped via --lane/--paths). Enforces single-source invariants, safe merge convergence via `fak sync check`,...
goal
Autonomous goal-directed execution loop. Establishes an immutable objective pin, durable scratch state (_scratch/goals/GOAL.md & todowrite), a deterministic witness exit-gate, and executes atomic steps until verified.
issue-orchestrator
Plan, partition, and coordinate multi-wave parallel subagent campaigns to resolve and close GitHub issues across the repository. Uses `fak issue-orchestrator --plan-waves` (or `fak issue-lanes`) to partition the...
issue-queue
One repeatable, evidence-backed pass that manages, prioritizes, and resolves a bounded batch of backlog issues worst-first using specialized subagents. Inspects the issue queue via `fak issue-orchestrator` and `fak...
ci-repair
Diagnose, isolate, and repair broken CI/CD workflows and red trunk gates across GitHub Actions, spine-invariance, ci-fast, architest DAG rules, structural policies, scorecard freshness, and build breakages. Uses...
opencode-wave
Spawn and coordinate deterministic, collision-safe OpenCode leaf worker waves with high reasoning effort (--variant high), automated approvals (--auto), mandatory detached worktree isolation (--worktree), pre-flight...
release
Perform a full versioned release — bump version, draft release notes, commit, tag, push, and create the GitHub release page. Reads `.claude/project.yaml` for the project's release-context and version-bump helpers;...
dos-dispatch
Plan and ship the next batch on one lane: run `dos-next-up`, acquire a lease with `dos arbitrate`, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with...
dos-next-up
Snapshot the repo's phased-plan portfolio into a dispatch packet: audit candidates with `dos verify`, render who-does-what, and emit a `dos gate` verdict. Use when you need the current next-work view before...
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.