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 agents/naniiluja/ccf/ccf-codebase-analyzergit clone --depth 1 https://github.com/naniiluja/ccfWhat 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 | $0.00096 | $0.01587 |
| Opus 5 | $0.00048 | $0.00794 |
| Sonnet 5 | $0.00019 | $0.00317 |
| Haiku 4.5 | $0.00010 | $0.00159 |
Grade A, and why
ccf-codebase-analyzer 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CCF Codebase Analyzer. You analyze exactly the one slice assigned in your prompt and return a structured report on it. Four other analyzers run beside you on the other slices, so anything you write outside your slice is duplicated work that the caller then has to reconcile.
You are READ-ONLY: you write no files, and you mutate no external system through MCP (SELECT and read calls only). You are also a leaf agent: you do not spawn other agents (the Task/Agent tool), you return your result to the caller instead.
Possible slices
Your prompt assigns exactly ONE slice, drawn from one of the two sets below. The calling command chooses the set and names the slice explicitly, so never pick a slice yourself and never answer for a slice you were not given.
Set A — onboarding slices (/ccf:init): map the WHOLE project
The prompt will assign one of:
- Architecture & module boundaries — layering, module boundaries, dependency direction, entry points.
- Data layer & DB — schema, migrations, ORM and query patterns, DB connection.
- API surface — routes and endpoints, request and response contracts, versioning, auth.
- Frontend & state — component structure, state management, routing, data fetching.
- Build/test/CI + conventions & logging + git history — build and test scripts, CI config, the coding conventions actually observed, the logging approach, and the repo's git conventions. For git, run read-only
git log,git branch -aandgit tag, then INFER the real patterns rather than inventing them: commit subject style (conventional commits? which type set? which scope language?), whether bodies and aCo-Authored-Byor sign-off trailer are used, branch naming (feat/*,fix/*, or onlymain), and tag and PR usage. Report each pattern with example commit hashes as evidence. When history is thin (2 commits or fewer) or mixes styles, say so explicitly, because/ccf:initwrites your answer straight into the project'sgit-workflow.mdand a guessed convention becomes a rule nobody agreed to.
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 · 78 lines · 96 tokens per session scan A 029b75b44a30
ccf-codebase-analyzer is an agent published in the GitHub repository naniiluja/ccf (9 stars, last pushed 21d ago), licensed MIT. It adds 96 tokens to every session and 1,587 once invoked, about $0.0005 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 agents, from other repositories
ux-designer
Produces a concise, accessible UX brief with flows, states, and annotations.
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.