cavekit is a Claude Code plugin that organizes software changes through a compact, spec-driven workflow stored in a SPEC.md file. It is for developers who want to plan, research, review, and build changes while preserving project context across sessions; the catalogue entries are its skills, commands, plugin configuration, and workflow rules.
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/juliusbrussee/cavekit/grillnpx skills add JuliusBrussee/cavekit --skill grillgit clone --depth 1 https://github.com/JuliusBrussee/cavekitWrote 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/juliusbrussee/cavekit/grill)<a href="https://agentmods.dev/skills/juliusbrussee/cavekit/grill"><img src="https://agentmods.dev/badge/skills/juliusbrussee/cavekit/grill.svg" alt="Measured on agentmods" 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 | $0.00129 | $0.00870 |
| Opus 5 | $0.00064 | $0.00435 |
| Sonnet 5 | $0.00026 | $0.00174 |
| Haiku 4.5 | $0.00013 | $0.00087 |
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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grill — sharpen idea before spec
One question at a time. Every answer lands in a § or gets parked ?. Never guess a constraint into existence.
Plan-then-execute guesses the fuzzy parts & builds the wrong thing. Grill drags the fuzz into §G/§C before a single §T row exists. A bad assumption caught here costs one question. Caught in §B it costs a bug.
WHEN TO GRILL
- Idea is one sentence & you can feel the holes.
- Multiple readings of the goal exist & you are about to pick one silently.
- Before
/spec newon anything non-trivial. - User asks to be challenged / stress-tested.
Skip for a typo or a one-line fix. Grill scales to uncertainty, ⊥ to ego.
CALIBRATE FIRST
One opening read, not a quiz:
- How well does user know this domain? (sets question depth)
- How locked is the idea? (exploring vs committed)
- Pressure wanted: light / normal / brutal.
Match it. Brutal grilling on a half-formed idea just demoralizes. Light grilling on a committed plan misses the load-bearing flaw.
QUESTION LADDER
Climb in order. Each rung, ask one question, recommend an answer, wait.
- Goal — what must the code do, in one line? (→ §G)
- Done — how do we know it works? name the observable. (→ §C / future §V)
- Boundary — what is explicitly out of scope? (→ §C)
- Lock — what tech/lib/pattern is non-negotiable? what is forbidden? (→ §C)
- Surface — what does the outside world touch — cmd, api, file, env? (→ §I)
- Edge — the one input that breaks the happy path? (→ future §V)
- Unknown — what do we not know yet? (→ park as
?§C bullet)
Stop climbing the moment the spec would be unambiguous. Do not ask all seven by reflex.
ANSWER FORMAT
Each question carries a recommended answer so the user can grunt "yes" & move:
Q: auth — session cookie or JWT? rec: JWT — stateless, you named horizontal scaling as a §C. (a) JWT (b) cookie (c) something else?
HANDOFF
When done, emit a compact block — goal line, constraint bullets, surfaced
unknowns as ? — and hand to the spec skill to write §G/§C. Grill proposes;
spec is the sole mutator. Never write SPEC.md directly.
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.
- 4d ago First seen · 83 lines · 129 tokens per session scan A 09548e80e581
grill is a skill published in the GitHub repository JuliusBrussee/cavekit (1,142 stars, last pushed 20d ago), licensed MIT. It adds 129 tokens to every session and 870 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
release-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
spec-writer
Create or refine spec-superflow planning artifacts. Invoke when the change is understood well enough to write proposal.md, specs/, design.md, and tasks.md.
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.