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/decision-capturenpx skills add bartoszarendt/agenticloop --skill decision-capturegit 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/decision-capture)<a href="https://agentmods.dev/skills/bartoszarendt/agenticloop/decision-capture"><img src="https://agentmods.dev/badge/skills/bartoszarendt/agenticloop/decision-capture.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 | $0.00078 | $0.01815 |
| Opus 5 | $0.00039 | $0.00907 |
| Sonnet 5 | $0.00016 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade A, and why
decision-capture 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 4d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision capture
Decision records are the small docs-first layer for durable project decisions. They are broader than the narrow ADR threshold. If a decision constrains future work and later agents would benefit from seeing it, it can earn a decision record even when it is not especially surprising or hard to reverse.
When to Use
Use this skill when a project decision needs a tracked Markdown record because it constrains future work. Common scopes include:
- process,
- architecture,
- backend choice,
- role boundaries,
- quality rules,
- security posture,
- release rules,
- product direction,
- accepted project conventions,
- verification.
Strong ADR-style signals such as hard to reverse, surprising, or tradeoff-heavy still matter, but they are not the only trigger.
Verification operating decisions
This is a promotion path, not timeout handling. First use
[[verification-evidence]] to record the task attempt. The maintainer then
triages it and, when the observation affects repeated project work, records or
updates the current VF-... fact in .agenticloop/project.md.
Use this skill for verification only when that already-recorded fact represents
a policy-level conclusion that constrains future work, such as a project rule to
use CI rather than local execution for a class of checks. The decision cites the
VF-... fact and its durable task/event evidence, states the policy and revisit
trigger, and follows the normal acceptance gate.
Do not use this skill for one timeout, ordinary timing noise, a retry choice, a task attempt, final timeout triage, or a mutable verification-fact update. Engineers report those observations; delegation observations never approve a strategy. A decision is not created merely because a check is expensive.
When Not to Use
Do not create a decision record for:
- ordinary task notes,
- implementation summaries,
- raw meeting notes,
- raw chat transcripts,
- temporary debugging observations,
- one-off local experiments that do not constrain later work,
- a current, non-binding project operating fact – record it in
## Project Operating Factsin.agenticloop/project.mdinstead, - a compact pointer to a runbook – that is a Project Operating Fact, not a decision.
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.
- 4d ago First seen · 200 lines · 78 tokens per session scan A 5a83333c5ecc
decision-capture is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 14d ago), licensed MIT. It adds 78 tokens to every session and 1,815 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.…