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/opencoven/coven/coven-task-managernpx skills add OpenCoven/coven --skill coven-task-managergit clone --depth 1 https://github.com/OpenCoven/covenWrote 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/opencoven/coven/coven-task-manager)<a href="https://agentmods.dev/skills/opencoven/coven/coven-task-manager"><img src="https://agentmods.dev/badge/skills/opencoven/coven/coven-task-manager.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 5.1 | $0.00040 | $0.00812 |
| Opus 5 | $0.00020 | $0.00406 |
| Sonnet 5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
coven-task-manager 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coven Task Manager
Use this skill when asked to manage, refresh, audit, triage, or summarize Coven tasks, or when a scheduled automation asks for task-board freshness.
Sources
Start with the Cave task board from the skill directory:
node ./task-manager.mjs report
The helper reads ~/.coven/cave-board.json and writes ~/.coven/task-manager/freshness-report.md by default.
If the canonical repo path is different, run the helper from this skill directory:
node ./task-manager.mjs report --coven-home ~/.coven
Workflow
- Load the task board and build a freshness report.
- Inspect the report sections in this order:
Stale Running,Needs Human,Ready For Review, thenNext Actions. - Read
Thread Coordinationbefore touching individual cards. Treat it as the concurrency control surface for simultaneous sessions. - For every active/review/blocked thread, build a small ledger: card id/title, familiar, session id, repo/branch/worktree if known, last evidence checked, current state, and one next action.
- Resolve collisions before dispatching new work:
- If multiple cards share a session, resume that session once and update all linked cards from the same evidence.
- If one familiar has multiple active lanes, choose the primary lane and mark the rest as waiting, review, or blocked with a reason.
- If multiple lanes touch the same repo or branch, verify branch/worktree ownership before allowing parallel writes.
- Prefer resuming a viable linked session over starting a new thread; start a fresh thread only when no current session can be resumed.
- For each task that needs action, gather concrete evidence before changing state: linked sessions, git branches, PRs, CI, user messages, or task notes.
- Keep task state fresh:
- Move stale running work only when evidence shows it is blocked, ready for review, done, or abandoned.
- Keep blocked tasks explicit: include the blocker, owner, and smallest next unblock action.
- Move review tasks only after the actual review/CI state is checked.
- Mark work done only when merge, delivery, or acceptance evidence exists.
- Update the freshness report after meaningful changes.
What ships with it
6 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.
- 6d ago First seen · 79 lines · 40 tokens per session scan A df1c89a6eef6
coven-task-manager is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 812 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 2026-08-30.
Other skills, from other repositories
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
babysit-babysitter-issues
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
project-tasks
Use this protocol to create, update, execute, or complete the structured projecttasks backlog in a Project conversation.
swarm-orchestration
Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.
constitution-creation
Establish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.