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 skills/raisedadead/claude-code-plugins/grillnpx skills add raisedadead/claude-code-plugins --skill grillgit clone --depth 1 https://github.com/raisedadead/claude-code-pluginsWhat 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 | $0.00140 | $0.01451 |
| Opus 5 | $0.00070 | $0.00726 |
| Sonnet 5 | $0.00028 | $0.00290 |
| Haiku 4.5 | $0.00014 | $0.00145 |
Grade A, and why
grill 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:grill — interrogate before you scaffold
A vague goal yields vague tasks. This formalises ds:new step 2's "clarify before freezing" into a bounded interrogation: facts get looked up, decisions get asked, and the output is an artifact ds:new consumes without re-asking.
Inputs
<slug>— dossier slug this grill feeds (kebab-case, same rules asds:new).--resume— reopen an incomplete artifact; open frontier nodes resurface.
Artifact
.scratchpad/dossier/.grill/<YYYY-MM-DD>-<slug>.md — dated at grill START. ds:new rediscovers it by SLUG (newest artifact wins), so a grill spanning days (--resume, pending-external waits) still gates the scaffold. On consume, ds:new stamps a CONSUMED: <dossier-dir-key> line into the artifact, so one grill feeds one dossier and a collision-bumped slug (<slug>-2) starts fresh.
FACT: <statement> cite=<file|command|url>
DECISION: <question> recommended=<x> answer=<operator verbatim>
DECISION: <question> recommended=<x> answer=pending-external → <questionnaire path>
FRONTIER: empty | empty-except-external n=<k>
CONFIRMED: <ISO timestamp> operator="<verbatim confirmation>"
CONSUMED: <dossier-dir-key> (stamped by ds:new, never by grill)
Footer lines are the machine-checked half: hooks/lib-assert-grill.sh exits non-zero on a half-grilled slug. No hook runs it — ds:new invoking the script and refusing on its exit is model-judgment, the same split as the tiger route: the verdict is computed, arriving at it is not.
One entry per paragraph — blank line between every FACT/DECISION/footer line. Markdown formatters join adjacent bare lines into one paragraph, which un-anchors the ^FRONTIER:/^CONFIRMED: greps and turns a complete artifact into a false "incomplete" (the failure class FORMAT.md §11 solves for §S).
Steps
0. Detect host env
Per ADAPTERS.md. An absent adapter is a skip.
1. Build the tree
Read what the operator has said so far plus the repo state (existing dossiers, git log, configs). Tag every open node:
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.
- 2d ago First seen · 99 lines · 140 tokens per session scan A f2f3b03e06ea
grill is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 7d ago), licensed ISC. It adds 140 tokens to every session and 1,451 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…