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 kochetkov-ma/claude-brewcode --skill task-board-setupgit clone --depth 1 https://github.com/kochetkov-ma/claude-brewcodeWrote 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/kochetkov-ma/claude-brewcode/task-board-setup)<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/task-board-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/task-board-setup/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/kochetkov-ma/claude-brewcode/task-board-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/task-board-setup.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 | $0.00019 | $0.01273 |
| Opus 5.5 | $0.00008 | $0.00509 |
| Sonnet 5.5 | $0.00004 | $0.00255 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade A, and why
task-board-setup 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 16d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex task-board initializer
Create exactly one Codex-owned file board; never create or mirror it under another assistant namespace.
Modes
Resolve exactly one canonical mode from status, install, upgrade, enable, disable, uninstall, purge -- a standalone token only, never a word that merely appears inside a sentence. With no mode given, a deployed board (.codex/features/board.md exists) resolves to status and an empty target resolves to install. init, on, off, setup, remove, reset, create, update and cleanup are not modes: read them as the canonical verb, echo the canonical name back, and never print a retired alias as a command.
| Mode | Effect |
|---|---|
status |
Read-only inventory of the target board. Writes nothing, delegates nothing, asks nothing. A parked .disabled twin is reported as parked, never as missing. |
install |
Run the phases below and deploy the board into the resolved target. |
upgrade |
Retrofit onto an already deployed board instead of the fresh-init phases. Recover the existing findings from the deployed artifacts rather than re-deriving them, ask for anything unrecoverable, write new files outright, and gate every edit of an existing file behind its own diff and confirmation. Never renumber and never delete. The metadata restamp is ungated and always runs -- it is the only thing that clears a stale version report. |
enable |
Restore parked machinery by renaming each .disabled twin back to the filename discovery keys on. Writes no content. |
disable |
First stop/verify this board's active session reminders, then park the task-tracker agent, board/spec skills and task rule as .disabled. Bodies and task data are kept. |
uninstall |
First stop/verify this board's active session reminders, then remove the generated agent, skills/rule and parked twins. Keep .codex/features/** as user data. |
purge |
uninstall plus deletion of .codex/features/**. Confirm first, stating the task counts that will be destroyed, and offer uninstall as the alternative that keeps them. |
What ships with it
16 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.
- agents/openai.yaml 253 B
- README.md 146 B
- references/01-analysis.md 13 KB
- references/02-task-tracker-agent.md 2.2 KB
- references/03-task-board-skill.md 2.5 KB
- references/04-tasks-rule.md 8.9 KB
- references/05-features-templates.md 28 KB
- references/06-doc-sweep.md 6.3 KB
- references/07-agents-md-optimize.md 15 KB
- references/08-task-spec-skill.md 24 KB
- references/09-spec-templates.md 12 KB
- references/10-upgrade.md 1.4 KB
- references/11-methodology-cron.md 7.8 KB
- references/12-verify-report.md 5.6 KB
- references/13-gated-placeholders.md 4.0 KB
- scripts/scope-guard.sh 4.3 KB runs code
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.
- 16d ago Changed · +8 lines 2a3f349830fb
- 1mo ago First seen · 50 lines · 19 tokens per session scan A 9a2361649a26
task-board-setup is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (33 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 1,273 once invoked, about $0.0001 per session on Opus 5.5. 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
work-planning
Design the complete work hierarchy for a Paperclip company — Goals, Projects, and Tasks as a unified top-down planning workflow. Produces .planning.json for deterministic generation of goals/, projects/, and tasks/ directories. Use when creating a new company's work plan, reorganizing work structure, or linking goals…
leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.
product-management
Product management expertise for product strategy, roadmap planning, feature prioritization (RICE, ICE, MoSCoW), customer research, A/B testing, product analytics, and product-market fit. Use when building product roadmaps, prioritizing features, or defining product strategy.
atlas-present
Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".
crest-narrative
Strategic narrative — write a standalone strategy memo that frames product direction, bets, and rationale for a planning horizon. Use when asked to "write a strategy doc", "product vision", "strategic narrative", "company strategy memo", "planning memo", or "explain our product direction".
hermit-scribe
File a GitHub issue or post a comment on an existing issue via a GitHub App bot identity. Use when the operator says "file as a GH issue", "open an issue for PROP-NNN", "report this to the tracker", "add a comment to issue.