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/progiri/craftlight/briefnpx skills add progiri/craftlight --skill briefgit clone --depth 1 https://github.com/progiri/craftlightWrote 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/progiri/craftlight/brief)<a href="https://agentmods.dev/skills/progiri/craftlight/brief"><img src="https://agentmods.dev/badge/skills/progiri/craftlight/brief.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 | $0.00232 | $0.02567 |
| Opus 5 | $0.00116 | $0.01283 |
| Sonnet 5 | $0.00046 | $0.00513 |
| Haiku 4.5 | $0.00023 | $0.00257 |
Grade A, and why
brief 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brief — decision by dialogue before the task
Principle: brief sits ABOVE plan and task. The discipline ladder: brief answers "what are we doing and
is it even worth it" (the result is a decision), plan answers "how to break the epic down" (the result is a DAG of
tasks and waves), task answers "how to execute" (the result is code). You take on brief when the direction isn't
chosen yet and the choice itself is the work. Ceremony is proportional: a discussion is just a conversation, until
the commit gate not a single file exists, a dead discussion is free. The one discussing neither executes nor
decomposes — they work out a decision, commit it, and hand it off.
Not for this skill: a stated task, even with a couple of open questions → task (inside its M/L there's a "spec
brief" — a phase that refines an already-accepted direction, don't confuse it with this skill); a chosen initiative
that just needs breaking into tasks → plan; "how does this work", a review, a one-off opinion question → a normal
answer. Realized along the way that the direction is already chosen and there's nothing to discuss → leave and hand
off to task or plan.
Step 0. Orientation and resume
There's a CRAFT.md → read it first: the project map, the starting point. The craftlight block upsert in the root
CLAUDE.md (reference and procedure — skills/task/templates/CLAUDE-block.md) rides with brief's first write to
disk — the saved pre-gate draft or the Step 3 artifact, whichever comes first — never earlier: until then brief
writes no files, and a call that never writes must not edit the user's CLAUDE.md.
- The message is a question about a past decision ("what did we decide about X") → this is a read, not a
resume: grep the verdict lines of
docs/crafts/*/BRIEF.md, answer from the matching brief, no resume ceremony. - A
docs/crafts/*/BRIEF.mdwith statusdraft(an unfinished discussion saved before the commit gate) and the message is a bare resume trigger ("continue the discussion", "back to the brief") → show the last "Decided: … / Remaining: …" from the Log and offer to continue: the brief is external memory, resuming reads the BRIEF, not the chat history. Several draft briefs → ask which one. - The message brings a new topic while a draft brief exists → discuss the new one; no blocking question —
one FYI line:
parked: brief "<slug>" is a draft — say "back to the brief" to resume it. - Refusal to resume → leave the draft in place; drop it only on an explicit request (status
abandoned). Resuming specs and plans is the concern oftaskandplan; brief operates only on briefs.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 122 lines · 232 tokens per session scan A f7e4f0f7f56d
brief is a skill published in the GitHub repository progiri/craftlight (5 stars, last pushed 10d ago), licensed MIT. It adds 232 tokens to every session and 2,567 once invoked, about $0.0012 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…