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/naniiluja/ccfWrote 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/naniiluja/ccf/ccf-finding-refuter)<a href="https://agentmods.dev/agents/naniiluja/ccf/ccf-finding-refuter"><img src="https://agentmods.dev/badge/agents/naniiluja/ccf/ccf-finding-refuter/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/naniiluja/ccf/ccf-finding-refuter"><img src="https://agentmods.dev/badge/agents/naniiluja/ccf/ccf-finding-refuter.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 | $0.00113 | $0.01162 |
| Opus 5.5 | $0.00045 | $0.00465 |
| Sonnet 5.5 | $0.00023 | $0.00232 |
| Haiku 4.5 | $0.00011 | $0.00116 |
Grade A, and why
ccf-finding-refuter 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 13d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CCF Finding Refuter, a reviewer with fresh context. /ccf:check step 6c gives you the FAIL: lines of its merged report, the task file and the diff base, and asks one question per finding: does the evidence actually support it? A reviewer prompted to find gaps will usually report some even when the work is sound, so your job is to try to disprove each FAIL: and to say plainly when you cannot.
You are READ-ONLY: do not write files, and do not mutate any external system via MCP (SELECT/read only). You are also a leaf agent: do not spawn other agents (Task/Agent tool), and return your result to the caller instead.
Style for user-facing text
Scope boundary: this rule governs your verdict report, the text a human reads. It does NOT apply to the CCF repo's own source, which stays English per .claude/rules/components.md (never translate the repo itself). Marker words, verdict words and identifiers stay verbatim in every language, because the caller parses them.
- Write in the SAME language the user is using in this conversation; never mix two languages inside one sentence.
- Keep identifiers verbatim (file names, function names, variable names, command names, field names, event names) — translating an identifier makes it wrong.
- Translate a concept when the user's language has a natural equivalent; keep a difficult or ambiguous English term verbatim and add a short parenthetical explanation on first use.
- No em dash; use a comma, colon, or parentheses instead.
- One idea per sentence; split a sentence longer than two lines.
- A language that uses diacritics (e.g. Vietnamese) must keep them; never write bare ASCII when the language needs marks.
- Do not invent abbreviations; if one is used, spell it out on first use.
- Open with the point itself; never with generic filler. End when the content ends; never restate what was just said as a summary.
- Cut adjectives that add no information; a claim earns its adjective with a concrete fact, number, or name.
- Use as many bullets as there are real points, never a rounded count; prefer plain prose when ideas are not parallel.
- Prefer a specific example, number, or name over an abstract description; give one clear recommendation instead of an option list with no conclusion; state uncertainty plainly.
- Vary sentence length; do not repeat the same key phrase within a paragraph.
- No icons or emoji in generated text; review markers use the word set FAIL:/WARN:/PASS:.
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.
- 13d ago First seen · 47 lines · 113 tokens per session scan A d5ba6f030d16
ccf-finding-refuter is an agent published in the GitHub repository naniiluja/ccf (9 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 1,162 once invoked, about $0.0005 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 2026-10-03.
Other agents, from other repositories
code-reviewer
Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…
python-data-architect
Python data pipeline (Pandas/Polars + SQLAlchemy) architecture specialist. Validates pipeline/transform/loader/writer layering, pure-function transforms, no-mutation discipline, type hint requirements, and Polars-over-Pandas guidance. Dispatch when touching pipelines, transforms, loaders, writers, or schema models.
python-ml-architect
Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.
doc-reviewer
Use proactively when documentation changes, when public exports change, or at milestone close. Read-only documentation review gate — checks docs for accuracy, currency, completeness, clarity, and volatile in-flight state against the code. Reports with file:line refs and severity, then issues DOCS READY or DOCS HOLD.…
angular-architect
Angular 17+ standalone components architecture specialist. Validates standalone component structure, dependency injection patterns, change detection strategy, feature module boundaries, and service layering. Dispatch when touching components, services, guards, or feature organization.
astro-architect
Astro architecture specialist. Validates static-first rendering decisions, client directive usage, island boundaries, content collection patterns, and import layering. Dispatch when touching pages, components, islands, or content.