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 commands/data-wise/craft/briefgit clone --depth 1 https://github.com/Data-Wise/craftWhat 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 | $0.00023 | $0.02656 |
| Opus 5 | $0.00012 | $0.01328 |
| Sonnet 5 | $0.00005 | $0.00531 |
| Haiku 4.5 | $0.00002 | $0.00266 |
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 yesterday.
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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/craft:brief
Generate the 3-line action block from live session context. Invoke explicitly when you want the block — replaces the auto-fire behavior formerly in research-session-defaults.md.
Block format
Next step: [concrete executable action]
Watch out for: [failure condition → exact mitigation]
Connects to: [exact artifact — branch, package, file, PR, or —]
Flags
| Flag | Effect |
|---|---|
| (none) | 3-line block only |
--plan |
Block + propose approach + 2–3 questions + mini-plan |
--verbose |
Expand each line with 1–2 sentences of context |
--show-context |
Display context sources before generating |
--board |
Ownership/state table above the 3-line block |
--board --plan |
Board + 3-line block + planning expansion |
--board --verbose |
Board + verbose-expanded 3-line block |
When invoked
Step 1: Synthesize context
Read sources in priority order. Stop at the first source that gives enough signal:
-
Conversation history (primary) — what topic was just discussed, what problem was active?
-
.STATUS next:field (secondary) — what's on deck?grep "^next:" .STATUS 2>/dev/null | head -1 -
Git branch + recent commits (tertiary) — what's being worked on?
git branch --show-current git log --oneline -3 -
ORCHESTRATE file + open PRs (quaternary) — what's in flight?
ls ORCHESTRATE-*.md 2>/dev/null | head -1 gh pr list --author @me --state open --limit 3 2>/dev/null
Step 1.5: If --board flag — infer owner/state rows
Read two sources already fetched in Step 1:
Source A: ORCHESTRATE-*.md (if present) — parse numbered list items and classify each:
| Pattern in item text | Owner | State |
|---|---|---|
| "auto", "agent will", "runs automatically", or git/CI shell commands | Me | 🟢 AUTO |
"wait for CI", "checks", "pending", or gh pr with no user action needed |
External | ⏳ WAITING |
| "merge", "approve", "decide", "review", "confirm", "choose" | You | 🔵 YOUR CALL |
| "blocked", "waiting on [external]" | You | 🔴 BLOCKED |
Leading ✅ |
— | ✅ DONE — omit unless --verbose |
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.
- yesterday First seen · 326 lines · 23 tokens per session scan A 611d43326540
brief is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 23 tokens to every session and 2,656 once invoked, about $0.0001 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 commands, from other repositories
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
readme-restructure
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
build-fix
Fix build and type failures with minimal diffs.
checkpoint
Record a verified checkpoint before the next phase.
doctor
Check the install surface for missing files and invalid manifests.
feature-dev
Drive a feature from plan to implementation to review.