Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add axiomantic/spellbook --skill finding-dead-codegit clone --depth 1 https://github.com/axiomantic/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/axiomantic/spellbook/finding-dead-code)<a href="https://agentmods.dev/skills/axiomantic/spellbook/finding-dead-code"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/finding-dead-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/axiomantic/spellbook/finding-dead-code"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/finding-dead-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.02520 |
| Opus 5.5 | $0.00026 | $0.01008 |
| Sonnet 5.5 | $0.00013 | $0.00504 |
| Haiku 4.5 | $0.00007 | $0.00252 |
Grade A, and why
finding-dead-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You never assume code is used because it "looks important." You never skip verification because "it seems needed." Professional reputation depends on accurate verdicts backed by concrete evidence. Are you sure this is all used?
Operate with skepticism: all code is dead until proven alive.
<CRITICAL_STAKES> Take a deep breath. Every code item MUST prove it is used or be marked dead. Exact protocol compliance is vital to my career.
You MUST:
- Check git safety FIRST (Phase 0) - status, offer commit, offer worktree isolation
- Ask user to select scope before extracting items
- Present ALL extracted items before verification begins
- Verify each item by searching for callers with concrete evidence
- Detect write-only dead code (setters called but getters never called)
- Identify transitive dead code (used only by other dead code)
- Offer "remove and test" verification for high-confidence dead code
- Re-scan iteratively after identifying dead code to find newly orphaned code
- Generate report that doubles as removal implementation plan
- Ask user if they want to implement removals
NEVER mark code as "used" without concrete evidence of callers. This is very important to my career. </CRITICAL_STAKES>
<ARH_INTEGRATION> When user responds to questions (authoritative inline definitions):
- RESEARCH_REQUEST ("research this", "check", "verify") -> Dispatch research subagent
- UNKNOWN ("don't know", "not sure") -> Dispatch research subagent
- CLARIFICATION (ends with ?) -> Answer the clarification, then re-ask
- SKIP ("skip", "move on") -> Proceed to next item </ARH_INTEGRATION>
Invariant Principles
- Dead Until Proven Alive - Every code item assumes dead status. Evidence of live callers required. No assumptions based on appearance.
- Full-Graph Verification - Search entire codebase for each item. Check transitive callers. Re-scan after removals until fixed-point.
- Data Flow Completeness - Track write->read pairs. Setter without getter = write-only dead. Iterator without consumer = dead storage.
- Git Safety First - Check status, offer commit, offer worktree BEFORE any analysis or deletion. Never modify without explicit approval.
- Evidence Over Confidence - Never claim test results without running tests. Never claim "unused" without grep proof. Paste actual output.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 256 lines · 66 tokens per session scan A f7891af2c7a4
finding-dead-code is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 2,520 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
simplify
Review recent code changes for reuse, code quality, and efficiency, then directly apply straightforward cleanup improvements. Use when the user wants a post-implementation cleanup pass, pre-PR polish, or asks to simplify/refine recent changes. Invoke with /simplify or /simplify .
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
review
Use when a green diff needs adversarial judgment in the rsc SDD chain, between verify and ship — give a review keyed to the spec/plan/constitution in 02-DOCS/wiki/sdd/, or receive one and verify each comment before agreeing. NOT running lint/type/tests (that is verify), NOT the spec-less standalone pass (that is…
code-review
Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…
critic-gate
Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.