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 agentmods add commands/axiomantic/spellbook/dead-code-analyzegit clone --depth 1 https://github.com/axiomantic/spellbookWhat 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 | $0.00028 | $0.02536 |
| Opus 5 | $0.00014 | $0.01268 |
| Sonnet 5 | $0.00006 | $0.00507 |
| Haiku 4.5 | $0.00003 | $0.00254 |
Grade A, and why
dead-code-analyze 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 2d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
Extract all code items from scoped files, present for user triage, verify each item's liveness via whole-codebase search, and re-scan to fixed-point.
Run after /dead-code-setup completes.
Prerequisites: Git safety completed, scope selected.
Invariant Principles
- Assume dead until proven alive - Evidence of usage clears the item; absence of evidence condemns it
- Evidence-based verdicts - Every verdict requires grep output, caller locations, or explicit proof
- Transitive analysis required - Code called only by dead code is itself dead; iterate to fixed-point
- Write-only detection - Setters without getter usage indicate dead features (entire feature unused, not just dead functions)
Phase 2: Code Item Extraction
Extract ALL added code items from scoped files.
What to Extract
| Item Type | Examples | How to Identify |
|---|---|---|
| Procedures/Functions | proc foo(), func bar(), def baz() |
Declaration lines |
| Types/Classes | type Foo = object, class Bar |
Type definitions |
| Object Fields | field: int in type definitions |
Field declarations |
| Imports/Includes | import foo, from x import y |
Import statements |
| Methods | Procs on objects, class methods | Method definitions |
| Constants | const X = 5, #define X |
Constant declarations |
| Macros/Templates | macro foo(), template bar() |
Macro/template defs |
| Global Variables | Top-level vars | Variable declarations |
| Getters/Setters | Accessor procs/methods | Property accessors |
| Iterators | iterator items(), for x in y |
Iterator definitions |
| Convenience Wrappers | Simple forwarding functions | Thin wrapper procs |
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.
- 2d ago First seen · 280 lines · 28 tokens per session scan A 5bf3859934f8
dead-code-analyze is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 2,536 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
audit-repo-docs
Audit repository documentation against 85+ best practices from claude-code-ultimate-guide.
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).