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 bendrucker/claude --skill grill-docsgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/grill-docs)<a href="https://agentmods.dev/skills/bendrucker/claude/grill-docs"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/grill-docs/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/bendrucker/claude/grill-docs"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/grill-docs.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 | $0.00033 | $0.00467 |
| Opus 5.5 | $0.00013 | $0.00187 |
| Sonnet 5.5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
grill-docs 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 1mo 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
Grill With Docs
Run the grilling skill's interview over $ARGUMENTS, and write each term and decision to disk as soon as it is settled.
Writing as we go is the point. If the session is compacted or abandoned, the repo still holds what we agreed.
Where It Lands
Choose both destinations before the first round and say them back to me.
Terms go where the repo already keeps instructions Claude loads automatically:
- A term that applies to one part of the repo goes in
.claude/rules/<area>.mdunder apathsentry, so it loads when that part is touched. - A term that applies everywhere goes in
CLAUDE.md. - Create the file if it does not exist.
Decisions go beside the plan that produced them, as <plan>-decisions.md in the same directory.
Vocabulary
Write a term as soon as it is settled, which means I have picked both the word and its meaning.
Prefer a word the codebase already uses. When the question is what to call something, search the codebase for candidates first and offer those as the options.
A definition says what the thing is and how it differs from the thing it is most easily confused with. Keep it to that.
Decisions
Record a decision when all three hold:
- Reversing it later would be expensive.
- Someone who was not in this conversation would not guess it.
- It was a tradeoff: a reasonable alternative was rejected.
Most sessions produce no decision that meets all three, and that is expected.
A record states the decision, the alternatives it rejects, and the tradeoff.
Close
Write the interview's closing escalation contract (what to proceed on without asking, what to stop and consult on) into the decisions file, then wait for me to confirm it.
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.
- 1mo ago First seen · 57 lines · 33 tokens per session scan A 9d2f250d5ba2
grill-docs is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 467 once invoked, about $0.0001 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 2026-09-11.
Other skills, from other repositories
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
ledger
OPS on-demand: This skill should be used when the user asks to "ops ledger", "what did we handle", or…
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…
vendor-management
Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…
handoff
Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work…