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 skills add naniiluja/ccf --skill grill-megit 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/skills/naniiluja/ccf/grill-me)<a href="https://agentmods.dev/skills/naniiluja/ccf/grill-me"><img src="https://agentmods.dev/badge/skills/naniiluja/ccf/grill-me/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/skills/naniiluja/ccf/grill-me"><img src="https://agentmods.dev/badge/skills/naniiluja/ccf/grill-me.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 | $0.00080 | $0.01871 |
| Opus 5 | $0.00040 | $0.00936 |
| Sonnet 5 | $0.00016 | $0.00374 |
| Haiku 4.5 | $0.00008 | $0.00187 |
Grade A, and why
grill-me 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grill-me — CCF requirements interview engine
A CCF command invoked you through the Skill tool. $ARGUMENTS carries the mode that selects which topics to cover:
plan— interrogate one feature/change before writing a sequential plan.fix— reconstruct a bug before debugging.init— elicit project decisions before bootstrapping CCF.
Run a focused interview under the discipline below, then hand a concise summary of the answers back to the calling command so it can continue.
Interview discipline (every mode)
- One question at a time. Ask, wait for the answer, and let that answer shape the next question. A batch of questions gets a batch of shallow answers, and it forfeits the chance to follow up on the one that mattered.
- Explore before you ask. Before each question, try to answer it yourself from the codebase (Read / Glob / Grep). Ask only what the code cannot tell you; for what it can, confirm instead of asking blind.
- Recommend with every question. Offer your recommended answer plus a one-line rationale, so the user can simply confirm. If the user defers, proceed with your recommendation and say which one you took.
- Stop when you have enough to act. Past the point of diminishing returns, more questions cost the user's patience and buy nothing.
- Summarize at the end. Give a short, structured recap of the decisions, ready for the command to fold into its next step.
Asking blind (wrong, the answer was one Grep away):
"How do you run the tests, and who calls parseRange?"
Asking a genuine unknown (correct, no artifact records the intent): "When two writers hit the same row, should the second one overwrite or fail loudly? I recommend fail loudly, so a lost update never happens silently."
Mode dispatch ($ARGUMENTS)
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.
- 9d ago First seen · 76 lines · 80 tokens per session scan A e17871499134
grill-me is a skill published in the GitHub repository naniiluja/ccf (9 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,871 once invoked, about $0.0004 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
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
hotfix
Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.
readme
This skill should be used to audit OR elevate the README of a public repository. Trigger with "improve the README", "make the readme high quality", "elevate this readme", "audit the readme", "add badges", "is our README good", or before publishing/releasing a repo. Elevate rebuilds a thin/generic README to a polished…
execute
Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.
ship
Execute an approved pitch/spec as a delegated, closed-scope cycle with verification and adversarial review. Invoke it yourself with /ship — a cycle spawns a writer and opens a PR, so it starts when you say so. Enforces the execution playbook: right-size gate, pre-spawn filter, doc-bundle, PR format, review.
graph
This skill should be used to design or run a task as a graph instead of a linear chain — fan out independent work across a fleet of subagents, verify findings, and converge. Trigger with "run this as a graph", "fan this out", "parallelize this", "orchestrate this with subagents", "audit every X", "sweep the codebase…