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 instructions/ruslano69/funcfinder/agents-mdgit clone --depth 1 https://github.com/ruslano69/funcfinderWhat 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 | $0.03493 | $0.03493 |
| Opus 5 | $0.01747 | $0.01747 |
| Sonnet 5 | $0.00699 | $0.00699 |
| Haiku 4.5 | $0.00349 | $0.00349 |
Grade A, and why
funcfinder AGENTS.md 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
funcfinder for AI Agents
Quick Reference: Map codebases, extract functions, trace calls, save 99% tokens.
Build First!
./build.sh # Required before first use (~5 sec)
Builds 5 binaries: funcfinder, stat, deps, complexity, callgraph.
The Toolkit at a Glance
| Tool | Purpose | Input |
|---|---|---|
funcfinder |
Map functions & types, extract bodies | file or dir |
deps |
Import dependencies + shard graph | dir |
callgraph |
Who calls whom | file or dir |
stat |
Call frequency & hotspots | file |
complexity |
Cognitive complexity per function | file |
Investigation Workflow
Small project (< 50 files)
# 1. Orient — full map in one shot (~30ms)
funcfinder --dir . --all --json > map.json
# 2. Find the target
grep -i "auth" map.json
# → auth/handler.go:42: AuthenticateUser
# 3. Extract the body
funcfinder --inp auth/handler.go --source go --func AuthenticateUser --extract
# 4. Trace who it calls
callgraph --inp auth/handler.go -l go --func AuthenticateUser
# 5. Trace who calls it (impact)
callgraph --dir . -l go --reverse --func AuthenticateUser
Large project (50+ files)
# 1. Split into shards (one-time, ~100ms)
funcfinder --dir . --all --json --split
# 2. Read manifest — 2KB overview of entire codebase
cat .codemap/manifest.json
# → see shards, function counts, depends_on links
# 3. Load the relevant shard
cat .codemap/internal_auth.json
# 4. Extract the function
funcfinder --inp internal/auth.go --source go --func Authenticate --extract
# 5. Check call graph for impact
callgraph --dir . -l go --reverse --func Authenticate
Incremental update (repeat sessions)
funcfinder --dir . --all --json --split --inc
# INFO: Incremental: 1 shards changed, 32 unchanged
Full architecture index (once per project)
# Build shard map
funcfinder --dir . --all --json --split --no-gitignore
# Add inter-shard dependency graph to manifest
deps . -l go --shards --no-gitignore --update-manifest .codemap/manifest.json
# manifest.json now contains:
# {"path": "cmd_funcfinder.json", "depends_on": ["internal.json"], ...}
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 · 420 lines · 3,493 tokens per session scan A 050b85949369
funcfinder AGENTS.md is an instructions file published in the GitHub repository ruslano69/funcfinder (2 stars, last pushed 20d ago), licensed MIT. It adds 3,493 tokens to every session, about $0.0175 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.