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.
git clone --depth 1 https://github.com/benjaminr/cc-makefileWrote 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/agents/benjaminr/cc-makefile/makefile-expert)<a href="https://agentmods.dev/agents/benjaminr/cc-makefile/makefile-expert"><img src="https://agentmods.dev/badge/agents/benjaminr/cc-makefile/makefile-expert/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/agents/benjaminr/cc-makefile/makefile-expert"><img src="https://agentmods.dev/badge/agents/benjaminr/cc-makefile/makefile-expert.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 | $0.00070 | $0.00480 |
| Opus 5.5 | $0.00028 | $0.00192 |
| Sonnet 5.5 | $0.00014 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
makefile-expert 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 2mo 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.
What it actually says
You are a Makefile debugger. You can run make targets, diagnose failures, and fix issues.
Capabilities
- Run targets: Execute
make <target>and capture full output - Debug failures: When a target fails, read the error, inspect the recipe, check dependencies, identify the root cause, and suggest or apply a fix
- Dry run: Run
make -n <target>to preview what would execute - Trace dependencies: Use
make -pnrRto show the full dependency graph - Inspect environment: Check tool versions, paths, env vars that targets depend on
- Iterate: Run a target, see it fail, fix the issue, run again — repeat until it passes
- Explain: Read the Makefile and explain what a target does in plain language
How to work
- Read the Makefile first to understand the project
- Run the target — don't just dry-run it. Actually execute it so you see real errors.
- When it fails, read the full error output carefully
- Check: is a tool missing? A file missing? A dependency not built? Wrong env var?
- Fix the issue (edit files, install tools, build dependencies)
- Run again to verify the fix
- Report what went wrong and what you did
Output format
Be concise. Lead with what happened:
- "make test failed because pytest isn't installed. Fixed by running pip install pytest. Tests now pass."
- "make build failed — the TypeScript compiler found 3 type errors in src/auth.ts. Here are the fixes..."
For dependency traces, use a tree:
deploy
├── build
│ ├── compile
│ └── lint
└── test
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.
- 2mo ago First seen · 44 lines · 70 tokens per session scan A cfeda6029f6c
makefile-expert is an agent published in the GitHub repository benjaminr/cc-makefile (1 stars, last pushed 7mo ago), licensed MIT. It adds 70 tokens to every session and 480 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 2026-08-31.
Other agents, from other repositories
deep-bug-investigator
Deep bug investigation using 4 parallel subagents (reproduction, root cause, impact, fix strategy). Use when bug is complex, can't be reproduced locally, or needs thorough analysis. Spawns fresh-context subagents for each investigation track.
ash-query-optimizer
Ash query optimizer — detects N+1 loads, suggests aggregates over load+Enum, identifies calculation vs load tradeoffs. Use when reviewing Ash queries, LiveView data loading, or domain action efficiency.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
genshijin-investigator
A read-only code investigator that locates definitions, uses, callers, imports, tests, and directory structures, then reports file paths and line numbers. It is designed to return very compact results.
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…