opus-pocus
01Plugin Claude Code
🪄 Wave wand over repo. Curses removed. Opus behaves. Spells that de-hex your Claude instructions for the Opus 5 era.
10 22d ago A
tokens not measured
original MIT
opus-pocus
02Plugin Claude Code
🪄 Wave wand over repo. Curses removed. Opus behaves. Spells that de-hex your Claude instructions for the Opus 5 era — remove verify-your-work incantations, death-spiral hooks, vague rules that summon demons, and automation that lies about its own state.
10 22d ago A
tokens not measured
original MIT
Agent
Read-only fan-out auditor for Opus Pocus passes — dispatched by the orchestrator or any single spell to scan one slice of a repo's Claude instruction layer (a directory of hooks, a set of memory files, an agent roster) against one spell's anti-pattern list, and report findings with file:line citations. Use when a…
10 22d ago A 121 tokens
original MIT
Skill Claude CodeCodex
Migrate path-bound instruction blocks out of the root memory file into scoped .claude/rules/ files with paths frontmatter, so rules load when Claude reads matching files instead of taxing every session. Use for "my CLAUDE.md has rules only relevant to one folder", "set up .claude/rules", "scope my rules to paths", or…
10 22d ago B 155 tokens
original MIT
alohomora
05Skill Claude CodeCodex
Audit blocking guards for over-reach — false positives that refuse legitimate work. Finds path resolution that treats out-of-scope paths as in-scope, guards applied to work outside the resource they protect, matching on symptom instead of emitter AND condition, missing or uncapped escape hatches, and block messages…
10 22d ago A 160 tokens
original MIT
Skill Claude CodeCodex
The ablation ritual — systematically remove instruction text and keep only removals that don't measurably hurt. Much instruction text is compensation for model weaknesses that no longer exist, and nobody measures which. Use for "is all this CLAUDE.md text even doing anything", "run an ablation", "my instructions grew…
10 22d ago A 158 tokens
original MIT
Skill Claude CodeCodex
Audit the repo's Claude instructions for vague rules — rules with no trigger, no scope, or no falsifiable condition. The 5-family reaches wider for instructions than older models, so a vague rule doesn't get ignored, it gets applied everywhere and dilutes the rules that matter. Use for "Claude over-applies my rules"…
10 22d ago A 133 tokens
original MIT
configure
08Skill Claude CodeCodex
Choose which Opus Pocus spells load in a session by writing per-skill skillOverrides entries to your settings, so a small repo carries three spells instead of all of them and pays only for what it uses. Detects the repo's shape, recommends a profile (greenfield / minimal / standard / full / maintenance), shows the…
10 22d ago B 182 tokens
original MIT
Skill Claude CodeCodex
Audit the repo's Claude instructions for contradictory rule pairs — rules where obeying one violates the other, or where a general rule and a specific rule collide with no stated precedence. The 5-family obeys widely, so it hits both rules of a contradiction and either freezes, alternates, or silently picks one. Use…
10 22d ago A 135 tokens
original MIT
Skill Claude CodeCodex
Audit every skill and agent description against the router's truncation cliff — the router selects on the description alone, listings truncate long descriptions (1,500 chars in some harnesses), and routing-critical clauses written last silently vanish. Use for "the wrong agent keeps getting picked", "my skill never…
10 22d ago A 122 tokens
original MIT
Skill Claude CodeCodex
Audit the repo's Claude instructions for self-correction death spirals — verify-your-work prompts, Stop/advisory hooks that re-fire on unchanged state, unbounded review→fix→re-review loops, and obligations that can never be discharged. Use for "Claude keeps re-checking itself", "the session never ends", "hooks keep…
10 22d ago A 119 tokens
original MIT
Skill Claude CodeCodex
Fetch the CURRENT official and community guidance on structuring repos for Claude's newest models before auditing or changing anything — Anthropic docs, the Claude Code changelog, and credible practitioner writing. Best practices for the 5-family are still being figured out in public and drift fast; an audit…
10 22d ago A 139 tokens
original MIT
Skill Claude CodeCodex
Measure and reduce per-prompt hook injection — the context every hook adds to every turn (SessionStart, UserPromptSubmit, PostToolUse, Stop advisories). Ranks emitters by tokens injected, finds false-positive matchers (bad keyword regexes, over-broad triggers), and prescribes fixes so hooks speak when relevant and…
10 22d ago A 140 tokens
original MIT
Skill Claude CodeCodex
Audit whether every check in the repo can tell "passed" apart from "never ran" — empty input reported as clean, filters that narrow the verdict as well as the output, exit codes read where the artifact is the evidence, skipped steps reported as passed, and reports with no denominator. Use for "the lint says clean but…
10 22d ago A 155 tokens
original MIT
Skill Claude CodeCodex
Put memory files (CLAUDE.md, AGENTS.md) on a diet — find fossils (migration-relative phrasing, "this used to say X" narratives, dated retractions living in the hot path), typed facts that drift (hand-written counts, sizes, versions), and history that belongs in an archive. The 5-family reads the whole file every…
10 22d ago A 163 tokens
original MIT
opus-pocus
16Skill Claude CodeCodex
The grand ritual — run the Opus Pocus audit passes over this repo's Claude instruction layer (memory files, hooks, skills, agents) and its automation layer, then emit The O.W.L. report with a grade per spell and a fix table you approve from. Triages first, so passes with no subject in your repo are marked N/A rather…
10 22d ago A 176 tokens
original MIT
Skill Claude CodeCodex
Audit whether every automation artifact is actually reached — hooks whose declared event does not match their wiring, orphaned skills/agents/commands/tests, artifacts that exist but nothing ever causes to run, and artifacts that work only because of local state a fresh clone lacks. Use for "is this hook even firing"…
10 22d ago A 153 tokens
original MIT
protego
18Skill Claude CodeCodex
Install a write-time hook that checks instruction artifacts as they are edited, so the defects the audit passes hunt stop accumulating between rituals — the one spell in this book that ships a mechanism rather than prose. Runs only the checks a script can decide without a model: emphasis inflation, descriptions past…
10 22d ago A 160 tokens
original MIT
Skill Claude CodeCodex
Audit the repo's Claude instructions for emphasis that over-applies on the 5-family — CRITICAL/YOU MUST/NEVER-EVER incantations, all-caps sentences, threats, and stacked warnings. The 5-family over-obeys emphasis: shouted rules get treated as globally binding while calm rules get under-weighted; when everything is…
10 22d ago A 143 tokens
original MIT
sorting-hat
20Skill Claude CodeCodex
Audit and assign model tiers to every agent in the repo — classify each as planner, builder, or judge, and pin an explicit model per role so expensive models plan and judge while cheaper models execute. Use for "which agents should run on which model", "cut my token spend", "set up model tiers", "Opus is doing grunt…
10 22d ago A 118 tokens
original MIT
Skill Claude CodeCodex
Apply a model-era delta to this repo's instruction layer — establish from evidence which model family the files were written for, then list what current guidance changes, as edits to your files rather than as research. Use for "these instructions were written for an older model", "what changed for the 5-family", "are…
10 22d ago A 165 tokens
original MIT
the-pensieve
22Skill Claude CodeCodex
Instrument the repo for a measurement week after instruction-layer changes — count what actually happens (advisory re-fires, review-loop rounds, subagent bounces, tokens injected per prompt, session outcomes) so the next round of changes is decided by numbers, not vibes. Use after landing /opus-pocus fixes…
10 22d ago A 139 tokens
original MIT
Skill Claude CodeCodex
Mine the repo's own session transcripts for places the human corrected the agent, cluster them, and derive which instruction is missing, wrong, or being ignored — the evidence-first inverse of every other pass, which read text and reason about it. Use for "what do I keep having to tell it", "why does it ignore that…
10 22d ago A 162 tokens
original MIT
Skill Claude CodeCodex
Author a first memory file for a repo that has none — derived from the repo's actual build/test commands, its real conventions, and its correction history, never invented. The one generative pass in this book: it proposes a file, you approve it, exactly like any other fix-table row. Use for "this repo has no…
10 22d ago A 169 tokens
original MIT