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 ulises-jeremias/agent-toolkit --skill decision-loggit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/decision-log)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/decision-log"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/decision-log/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/ulises-jeremias/agent-toolkit/decision-log"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/decision-log.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 | $0.00032 | $0.00190 |
| Opus 5 | $0.00016 | $0.00095 |
| Sonnet 5 | $0.00006 | $0.00038 |
| Haiku 4.5 | $0.00003 | $0.00019 |
Grade A, and why
decision-log 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 9d 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.
What it actually says
Decision Log (WHAT)
Use for lightweight decisions made in meetings or project discussions.
Choose the right artifact
- Use
decision-logfor lightweight operational, product, or project decisions. - Use
agreementfor explicit commitments or terms among parties. - Use
adrfor durable architecture or technical decisions.
Default guardrails
- Apply
output-handshakebefore final output. - Link related work items and meeting minutes where possible.
References
references/default-template.mdreferences/example-repository-pattern.md— example decision log entry for a data access layer migrationmeeting-minutesadr
What ships with it
2 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.
- 9d ago First seen · 29 lines · 32 tokens per session scan A d36e09995230
decision-log is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 190 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
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
iblai-api-agent-skill
Manage an ibl.ai agent's skills via the platform API — browse the org skill catalog, assign/unassign skills to an agent, and create/edit/delete catalog skills. Requires a connected sandbox. Use when giving an agent reusable skill instructions.
iblai-api-agent-safety
Configure an ibl.ai agent's moderation and safety systems via the platform API — enable flags, system prompts and responses (saved through the agent settings endpoint) — and review or delete flagged-prompt moderation logs. Use when setting guardrails or auditing flagged content.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
vibeflow-quick
Fast-tracks small tasks into a prompt pack in one command. Skips discover, generates an ephemeral spec in memory. Use for well-defined planned tasks that fit in ≤4 files — not for an observed defect with reproducible evidence (that's the vibeflow-hotfix skill).