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/bartoszarendt/agenticloop/task-closeoutnpx skills add bartoszarendt/agenticloop --skill task-closeoutgit clone --depth 1 https://github.com/bartoszarendt/agenticloopWhat 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 | $0.00111 | $0.03477 |
| Opus 5 | $0.00056 | $0.01739 |
| Sonnet 5 | $0.00022 | $0.00695 |
| Haiku 4.5 | $0.00011 | $0.00348 |
Grade A, and why
task-closeout 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 2d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task closeout
Closeout confirms that the relevant task set is actually complete, records durable evidence, and turns repeated process friction into follow-up work or skill improvements.
If the remaining request is cleanup of an accepted, integrated worktree, follow
the worktree cleanup lifecycle and human checkpoint in
agenticloop/AGENTIC_LOOP.md.
Cleanup does not replace closeout evidence or reopen accepted implementation.
Run closeout:
- for each configured group when
.agenticloop/project.mdsaysgroup_closeout: true, or - when a human-identified task set or work unit finishes, including in flat projects.
Closeout has two ordered parts. Closeout preparation may begin once covered tasks are accepted; it performs only the conditional source-plan synchronization below so that any permitted plan edit can be included in the final candidate. The final closeout gate runs after that resulting candidate is integrated or frozen and, when enabled, certified. It is a verify-and-mark gate and does not produce a separate summary artifact. The durable record is the per-task inline summary plus the backend (task files or GitHub issues/PRs); final closeout confirms that record is complete and posts a status marker.
Conditional source-plan progress synchronization
This section is the canonical procedure for source-plan progress synchronization during closeout preparation. It is deliberately conditional: closing a task does not authorize inventing a plan status convention or rewriting a target-owned plan.
- Resolve
documents.planfrom.agenticloop/project.md. If no selected plan exists, record no plan mutation and continue closeout normally. - Read only the selected plan's explicit instructions for maintaining progress or status, plus the task/work-unit source references that could map the completed work to one plan entry. Do not infer instructions from a plan's heading shape, prose tone, or unrelated checklist.
- Mutate the plan only when its explicit instructions define the allowed progress/status update, one relevant entry maps unambiguously to the closing work unit, and repository rules allow the mutation. Never invent a checkbox, percentage, status vocabulary, completion convention, or plan structure.
- Route this narrow plan edit to the single-writer Maintainer/closeout lane, never an Engineer implementation lane. Preserve unrelated target-owned plan content. If the requested state is already correct, make no rewrite.
- Record the plan path, affected section or item, previous state, new state, and covered task IDs in the closeout evidence or note. This evidence makes a rerun idempotent: it must neither duplicate the entry nor reapply an already correct state.
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.
- 2d ago First seen · 318 lines · 111 tokens per session scan A f3132d2b0a56
task-closeout is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 12d ago), licensed MIT. It adds 111 tokens to every session and 3,477 once invoked, about $0.0006 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 skills, from other repositories
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
consulting-analysis
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
deerflow-maintainer-orchestrator
Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation…
systematic-literature-review
Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Searches arXiv and outputs reports in APA, IEEE, or BibTeX format. Not for single-paper tasks — use academic-paper-review…
academic-paper-review
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation.…