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/loop-retrospectivenpx skills add bartoszarendt/agenticloop --skill loop-retrospectivegit clone --depth 1 https://github.com/bartoszarendt/agenticloopWrote 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/bartoszarendt/agenticloop/loop-retrospective)<a href="https://agentmods.dev/skills/bartoszarendt/agenticloop/loop-retrospective"><img src="https://agentmods.dev/badge/skills/bartoszarendt/agenticloop/loop-retrospective.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 | $0.00074 | $0.00722 |
| Opus 5 | $0.00037 | $0.00361 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
loop-retrospective 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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop retrospective
Loop retrospectives turn observed friction into durable process improvements. The output is never private memory; every retained lesson becomes reviewed text in the repo or a task record a later agent can discover.
This skill is parked and optional. It is not part of [[task-closeout]] and does not gate it. Run it only when a human explicitly asks for a retrospective, and only when there is enough recorded signal to work from. Its primary inputs are the local event logs and blocked/needs_context events – not task completion summaries, which are written for a different purpose. Until event logging matures into routine use, this skill will usually have nothing durable to act on; that is expected.
Workflow
- Gather signals. Read the local
.agenticloop/logs/<TASK-ID>.jsonlevent log entries (when event logging is enabled and files exist), blocked and needs_context events, recorded block categories, review-result events across rounds, and recurring follow-up task topics. Do not reconstruct friction from task completion summaries or copy raw agent exchanges into docs. - Find recurring patterns. Treat repeated check failures, repeated block categories, repeated review rounds, and repeated follow-up themes as candidates. Do not turn one-off noise into new process. One directly evidenced required-gate bypass, fabrication, or material misordering is the narrow serious-incident exception: create one durable improvement proposal without waiting for repetition.
- Choose one durable artifact per pattern.
- Update a skill when the pattern is a recurring agent behavior or rationalization.
- Add a docs entry when the pattern is a durable out-of-scope decision, known limitation, or operational note.
- File a follow-up task record when the pattern requires implementation or human decision.
- Keep provenance visible. Cite grouping ids when relevant, task ids, artifact references, and command evidence. Do not promote interpretation into fact without evidence.
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.
- 3d ago First seen · 59 lines · 74 tokens per session scan A 67d35c12fc0f
loop-retrospective is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 13d ago), licensed MIT. It adds 74 tokens to every session and 722 once invoked, about $0.0004 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.…