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/w2ur/claude-code-setup/briefgit clone --depth 1 https://github.com/w2ur/claude-code-setupWhat 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 | $0.00031 | $0.00529 |
| Opus 5 | $0.00015 | $0.00264 |
| Sonnet 5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
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.
What it actually says
Print the queue, then name what would clear it. Do not run any of the commands you name.
Step 1 — run the aggregator
~/.claude/scripts/intendant.sh
It is deterministic and no-model; you are only reading and routing its output.
Step 2 — read the exit code, and say what it means
| exit | meaning | what to say |
|---|---|---|
| 0 | nothing needs the owner | "Nothing needs you." Stop there. |
| 1 | the queue is non-empty, every source answered | present the queue |
| 2 | at least one source could not be read | present the queue and lead with what is unknown |
Exit 2 is the one that matters. It means part of the sweep did not run, so the
queue is incomplete by an unknown amount. Any SIGNAL LOST: line must be repeated at
the top of your reply, in the owner's language, and the queue below it explicitly
described as partial. Never summarise an exit-2 run as "not much to do today" —
a short queue and a dead input look identical, which is the exact failure this script
exists to prevent.
Step 3 — offer the one or two commands that clear the top items
Map, name at most two, and let the owner choose:
| queue source | command to offer |
|---|---|
vigie — CI gate missing, env drift |
/tech-debt |
vigie — plans past the archive cutoff |
/cleanup |
jobs — an agent exited 2 |
read its log; the path is in jobs-inventory.sh --json |
Rules
- Report state. Never act. This command opens nothing, edits nothing, dispatches nothing. Naming a command is the whole job; the owner decides.
- Do not re-derive the counts. The script owns them. Restating a number you did not read from its output is how prose drifts away from the artifact.
- Keep it short. This is a queue you read in ten seconds, not a report.
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 · 50 lines · 31 tokens per session scan A b76ddcd053e4
brief is a command published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 529 once invoked, about $0.0002 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
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
icon-lookup
Search for icons by name, or identify a PUA character.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
adr
Architecture Decision Record (ADR) command. Documents architectural decisions in a structured format.