cascade-dedup

Solid

Use when prompt-doctrine is duplicated, drifted, or conflicting across output-style embeds and external harness AGENTS files. Strips duplicate directives from persona prefixes, repairs invariant-zone tail drift, classifies harness divergences, and records a divergence ledger before committing. Not for editing the canonical baseline itself.

AI & Automation 35 stars 0 forks Updated 2 days ago Apache-2.0

Install

View on GitHub

Quality Score: 82/100

Stars 20%
52
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Cascade dedup ## Contract | Field | Bound contract | |---|---| | Trigger | Prompt-doctrine duplication, drift, or conflict across the cascade family. | | Authority | Human-only. Require explicit human invocation; preview the target and consequence before rewriting prompt doctrine at rest, bumping the catalog `releaseVersion`, or editing authorized external harness embeds. | | Side effect | Rewrites cascade prefixes/tails, bumps the catalog `releaseVersion` and re-renders package surfaces, and edits authorized external embeds. | | Done | All canonical tails match, every strip is evidenced, divergence ledger complete, verification green. | ## Inputs - The canonical baseline file `system-prompt-baseline.md` — must exist and be the agreed source of truth. - The six output-style embeds: `packages/odin-core/output-styles/{axiom-mode,builder,duet,linus,odin,benchmark}.md`. - The two external harness embeds: `~/.omp/agent/AGENTS.md` and `~/.codex/AGENTS.md`. - Explicit user authorization, recorded in the run, before any `benchmark.md` tail repair or authorized external embed edit. ## Procedure 1. **Map the cascade family and zones.** The canonical baseline `system-prompt-baseline.md` is the whole-file source of truth and wins every conflict. For each output-style embed (`axiom-mode`, `builder`, `duet`, `linus`, `odin`, `benchmark`), the persona prefix above the charter `<role>` (the second `<role>` in each file) is the strip zone. The tail from the charter `<role>` to EOF is ...

Details

Author
OutlineDriven
Repository
OutlineDriven/odin-claude-plugin
Created
9 months ago
Last Updated
2 days ago
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

dedup-skills

Use when asked to deduplicate skills or prompt directories, find repeated rules, or check a skill tree for contradictions. Produces a read-only ledger classifying every repetition cluster and conflict candidate with evidence and zero unclassified cells.

35 Updated 2 days ago
OutlineDriven
AI & Automation Listed

harness-bootstrap

Install or sync the generic harness runway in any repo — greenfield or with code present. Scaffolds CLAUDE.md, CODING_STANDARDS.md (headings-only), skeleton docs (overview, techstack, decisions, specs/, work/), path-scoped rules, and the core plugin pin; bakes in doc-sync discipline. On greenfield it writes empty product skeletons; stack-matched skill/MCP/hook curation is gated tier-2, orchestrated by /super-bootstrap; opt-in earn-gated scale module (parked + test-queue + outward containers, venue-map rule, card fact fields). Monorepo tier fans path-scoped rules out per package; adopt mode retires superseded harness forks and backfills skeleton sections added since bootstrap on re-run. Solo dev workflow.

3 Updated today
RockyHong
AI & Automation Listed

unhobble

Audit and rightsize a context surface — CLAUDE.md, AGENTS.md, a SKILL.md, a system prompt, or a single prompt — against the Claude-5 context-engineering reversals. Measures the surface (token budget, how much of it is phrased as hard rules vs judgment, near-duplicate sections, contradiction candidates, filesystem-derivable content, progressive-disclosure gaps), then adjudicates each section keep / relocate / delete using a grounding-aware predicate: prose backed by an independent mechanism is decorative and free to cut, prose that is the only carrier of a behavior is a real bet. Also rewrites prompts and skills from prohibition-form into judgment-form. Anthropic deleted >80% of Claude Code's system prompt for Claude 5 with no eval loss; this is the repeatable version of that cut. Use when: (1) a CLAUDE.md or AGENTS.md has grown and you want to know what is safe to remove, (2) an agent is ignoring or colliding with its own instructions, (3) a prompt is long and over-constrained and underperforming, (4) auditin

3 Updated today
broomva