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 skills/benmarte/codemunch/searchnpx skills add benmarte/codemunch --skill searchgit clone --depth 1 https://github.com/benmarte/codemunchWhat 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 | $0.00054 | $0.01024 |
| Opus 5 | $0.00027 | $0.00512 |
| Sonnet 5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
search 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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Skill
Find symbols without reading any files. Returns a compact index listing.
Search modes
By name (exact or fuzzy)
# Exact
jq '[.symbols[] | select(.name == "validateToken")]' .claude/codemunch/index.json
# Case-insensitive
jq '[.symbols[] | select(.name | ascii_downcase | contains("validate"))]' .claude/codemunch/index.json
# Fuzzy: split query into chars and find symbols containing all of them in order
# e.g. "vt" matches "validateToken", "visitTree"
By kind
# Find all classes
jq '[.symbols[] | select(.kind == "class")]' .claude/codemunch/index.json
# Find all exported functions
jq '[.symbols[] | select(.kind == "function")]' .claude/codemunch/index.json
# Kinds vary by language:
# TypeScript: function, class, method, property, interface, type, enum, constant, variable
# Python: function, class, method, variable
# Go: function, struct, interface, method, constant, variable, type
# Rust: function, struct, enum, trait, impl, method, constant, type
# Ruby: method, class, module, constant
# Java/Kotlin: class, interface, method, field, enum, constructor
# C/C++: function, class, struct, enum, method, field, typedef
By file
jq --arg f "auth" '[.symbols[] | select(.file | contains($f))]' .claude/codemunch/index.json
By container (class/module)
jq --arg c "AuthService" '[.symbols[] | select(.container == $c)]' .claude/codemunch/index.json
Combined
# All methods in a specific class
jq --arg c "Invoice" --arg k "method" \
'[.symbols[] | select(.container == $c and .kind == $k)]' \
.claude/codemunch/index.json
Output format
Always return a compact list — never the full source. Source is fetched separately with the fetch skill:
Found 6 symbols matching "validate":
1. validateToken function src/auth/tokens.ts:142 AuthService
2. validateInvoice function src/lib/validation.ts:89 —
3. validateAmount function src/lib/validation.ts:112 —
4. validateEmail method src/models/user.ts:34 UserModel
5. validateExpense function convex/expenses.ts:67 —
6. validateDateRange function src/utils/dates.ts:23 —
Use /codemunch:fetch <name> to read the source of any symbol.
Tokens used: 12 (vs reading 6 files: ~18,000 tokens)
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.
- yesterday First seen · 114 lines · 54 tokens per session scan A 2211a7cfc80b
search is a skill published in the GitHub repository benmarte/codemunch (7 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,024 once invoked, about $0.0003 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 skills, from other repositories
karting-advisor
KartSan — AI karting coach for youth racers (7-14) in Rotax Micro/Mini/Junior MAX. Bilingual EN/PT. Analyzes MyChron 5/5S/6 telemetry, TRAX data, Race Studio 3 exports, GPS trails, and screenshots. Builds interactive dashboards with track maps and overlays. Covers technique, setup, gearing, tires, jetting, Rotax…
r3f-animation
React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
golden-rss
Use when testing the rss golden build.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.