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 skills add HirogaKatageri/hirokata --skill briefgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/brief)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/brief"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/brief/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/brief"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/brief.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00147 | $0.04248 |
| Opus 5 | $0.00073 | $0.02124 |
| Sonnet 5 | $0.00029 | $0.00850 |
| Haiku 4.5 | $0.00015 | $0.00425 |
Grade A, and why
brief scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guild Brief — the narrated read of the board
Read-only. This skill reports; it never dispatches an agent, never moves a task, and
never writes a row. If the user wants work to start, that is guild:check-in.
Load guild:warehouse for the connection ritual and the view catalog. Everything below is a
SELECT. Your job is to turn those rows into a briefing a human can act on — guild:check-in
opens with the same reads, so what you write here is what the daily flow reads too.
Step 1 — is there a guild?
[ -f .guild/config.yaml ] || echo "no guild here"
If it is missing, say exactly this and stop:
No guild board found. Run /guild:check-in to initialize and start your first work session.
Step 2 — read the board
One script, one round trip. Write it with a quoted heredoc so the shell never touches the SQL:
export PATH="$HOME/.turso:$PATH"
cat > /tmp/brief.sql <<'SQL'
SELECT '## brief'; SELECT fact, value FROM v_brief;
SELECT '## direction'; SELECT id, priority, projects_runnable, runnable_project_ids,
requirements_done, requirements_total, title FROM v_goal_progress;
SELECT '## projects'; SELECT json_object('id',id,'goal',goal_id,'why',why,
'isolation',isolation,'worktree',worktree_path,
'title',title) FROM v_projects_runnable;
SELECT '## requirements'; SELECT id, status, tasks_done, tasks_total, tasks_open,
tasks_blocked, tasks_failed, title FROM v_requirement_progress
WHERE status <> 'done';
SELECT '## in-flight'; SELECT json_object('id',id,'req',requirement_id,'who',who,
'minutes',minutes,'title',title) FROM v_in_flight;
SELECT '## bounties'; SELECT json_object('id',id,'req',requirement_id,'p',priority,
'who',who,'title',title) FROM v_open_bounties;
SELECT '## blocked'; SELECT json_object('id',id,'req',requirement_id,'status',status,
'reason',reason,'title',title) FROM v_blocked_tasks;
SELECT '## bugs'; SELECT json_object('id',id,'sev',severity,'status',status,
'by',found_by,'req',requirement_id,'title',title) FROM v_open_bugs;
SELECT '## failed'; SELECT json_object('id',id,'who',who,'waived',waived,
'reason',COALESCE(reason,''),'title',title) FROM v_failed_tasks;
SELECT '## findings'; SELECT json_object('id',id,'task',task_id,'sev',severity,
'disp',disposition,'by',reviewer,'at',
COALESCE(file,'') || ':' || COALESCE(line,''),
'what',summary) FROM v_open_findings;
SELECT '## coverage'; SELECT json_object('id',id,'risk',risk,'due',interval_days,
'since',COALESCE(days_since,-1),'area',area) FROM v_coverage_due;
SELECT '## docs-stale'; SELECT json_object('slug',slug,'kind',kind,'subject',
subject_type || ':' || subject_id,'moved',subject_moved_at,
'title',title) FROM v_doc_stale;
SELECT '## undocumented'; SELECT json_object('id',id,'at',finished_at,'title',title)
FROM v_undocumented_work;
SELECT '## gates'; SELECT json_object('node',node_id,'req',requirement_id,
'kind',kind,'prompt',prompt) FROM v_gates_pending;
SELECT '## approvals'; SELECT json_object('id',id,'req',requirement_id,'status',status,
'gate',gate_node_id,'title',title)
FROM v_plans_pending_approval;
SELECT '## moved'; SELECT json_object('ts',ts,'actor',actor,'verb',verb,
'type',subject_type,'id',subject_id,'title',subject_title,
'phrase',phrase) FROM v_recent_activity
WHERE ts >= COALESCE(NULLIF((SELECT value FROM guild_state
WHERE key='last-checkin'),'null'),'')
ORDER BY ts DESC LIMIT 30;
SQL
tursodb -q -m list .guild/guild.db < /tmp/brief.sql
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.
- today Changed 613d2bec4f8e
- 5d ago First seen · 262 lines · 147 tokens per session scan A 5f5a832a261d
brief is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 4,248 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 2026-09-04.
Other skills, from other repositories
crm-management
Use when an internal 101 goal must manage CRM pipelines, stages, deals, or distribution rules through the current CRM API.
estimate-management
Use when an internal 101 goal must find, read, create, or edit one or many estimates through the existing event API, including sourced or manual positions and their dates.
project-management
Use when an internal 101 goal must create or edit a project, select its customer or price list, manage project expense categories, or copy category settings from another project.
task-management
Use when an internal 101 goal must list, read, open, update, or comment on tasks, including the interactive task detail widget.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…