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 OutlineDriven/outline-driven-development --skill decision-diarygit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/decision-diary)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/decision-diary"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/decision-diary/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/outlinedriven/outline-driven-development/decision-diary"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/decision-diary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00707 |
| Opus 5 | $0.00020 | $0.00353 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
decision-diary 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision diary
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to record why one world won over the others. |
| Authority | Reversible local: writes only one decision-diary entry at the agreed diary location; rollback is version control. No remote mutation. |
| Side effect | A decision-diary entry documenting why one world won. |
| Done | The decision and its rationale are recorded in the decision diary. |
Inputs
Winning decision: the world or option that won. Required. Considered worlds: every option that was on the field, including the winner. Required. Rationale: why the winning world won and why each rejected world lost. Required. Decision-diary location: the local file path where the entry is appended. Required; if no location is established, the user must supply it. Optional inputs: date, surrounding context, human opinions, agent doubts, and obvious assumptions that shaped the choice.
Procedure
- Confirm the winning decision and the full set of considered worlds from the user. Do not infer a winner or invent options that were not on the field. Done when: the winning decision and all considered worlds are confirmed from the user.
- Capture why the winning world won, using the user's terms. Done when: the winning rationale is recorded in the user's own terms.
- Capture, for each rejected world, the reason it lost. Done when: every rejected world has a loss reason recorded.
- Record any human opinions, agent doubts, and obvious assumptions the user names as load-bearing for the choice. Omit this section when the user names none; do not fabricate doubts or assumptions. Done when: named opinions, doubts, and assumptions are recorded, or the section is omitted because the user named none.
- Compose one diary entry containing the winning decision, the considered worlds, the winning rationale, the per-rejected-world loss reasons, and any named opinions, doubts, or assumptions. Done when: the entry contains all five elements.
- Append the entry to the decision-diary file at the agreed location. Create the file only if the user confirms it does not yet exist and names this path as its home. Done when: the entry is appended to the diary file at the agreed location.
- Read the entry back from the diary and confirm it is persisted and readable. Done when: the entry is read back and confirmed persisted and readable.
What ships with it
1 file 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.
- 2d ago Changed · -6 tokens per session ff6defde278c
- 5d ago First seen · 43 lines · 46 tokens per session scan A faf5a447bdd9
decision-diary is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 707 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.