agentleFS
Sign inStart free
Sapere-IASapere-IA/sdd-onboarding-kit/skills/optional/decision-log/SKILL.md

decision-log

Skill19 starsChanged 37 days agoMITView on GitHub

Record durable architectural and workflow decisions in the project's decision log. Use when a spec, review, or discussion settles something future sessions must not re-litigate.

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use product-brief, pre-mortem and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • erik-kroonSkill

    product-brief

    Turn conversation context, codebase findings, and product intent into a PRD-style brief without assuming a specific issue tracker. Use when the user wants a PRD, product brief, feature spec, or implementation-ready product artifact.

    Also in 3 projects that use this

  • Ingramradical235Skill

    pre-mortem

    Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.

    Also in 3 projects that use this

  • MicrosoftSkill

    retrospective

    Review how work went and improve the next round. USE WHEN asked for a retro, delays, or process lessons. DO NOT USE for code review or transcript replay.

    Also in 4 projects that use this

  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    test

    Also in 3 projects that use this

  • HashiCorpSkill

    changelog

    Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the decision contradicts an earlier entry, mark the old entry as superseded rather than deleting it.

    line 63
  2. Very specific:

    If the rule is load-bearing for every session, additionally propose a one-line AGENTS.md rule (see reference/memory-policy.md in the kit: …

    line 65
  3. Distinctive:

    Never write an entry without developer approval of the exact text.

    line 78
  4. Distinctive:

    Never log secrets, credentials, or personal data.

    line 79

“Common” is measured: kept by at least 6 in 10 of the 39 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Decision log

Purpose

Make significant decisions survive context compaction and new sessions by recording them in versioned project files instead of chat history.

Where decisions live

  • decisions/answers.md — onboarding answers (always created at onboarding).
  • decisions/architecture-decisions.md — durable architectural choices.
  • decisions/rejected-options.md — alternatives considered and rejected.
  • decisions/workflow-decisions.md — agreed workflow rules ("from now on, X").
  • docs/adr/ — if the project already uses ADRs, architecture decisions go there in the project's existing format and numbering instead of architecture-decisions.md.

The locations configured for this project are recorded in decisions/answers.md (onboarding question §17). Each decision file carries its own entry format in its header.

When to use

  • A spec or review settles an architectural choice (and especially when an alternative was explicitly rejected).
  • A workflow rule is agreed with the developer ("from now on, X").
  • The same question keeps being re-asked across sessions.
  • The SDD workflow flagged a decision for logging: the spec-author reports significant decisions when a spec is ready, and the reviewer flags decisions settled during implementation or review (see workflow.md).

When not to use

  • Trivial choices with no future consequence (naming a local variable, one-off formatting).
  • One-off instructions that apply to a single task.
  • Speculative conclusions not yet confirmed by the developer.
  • Anything containing secrets or sensitive operational data.

Required inputs

  • The decision, its context, and the alternatives considered.
  • Which file it belongs in (architecture / rejected option / workflow rule, or an ADR).
  • The source task/spec/review the decision came from.

Procedure

  1. Confirm the decision is durable and non-trivial.
  2. Pick the target: architectural choice → architecture-decisions.md (or docs/adr/ if configured); rejected alternative → rejected-options.md; workflow rule → workflow-decisions.md.
  3. Draft the entry using the target file's entry format (date, status, context, decision, alternatives, consequences, source).
  4. Propose the exact entry text to the developer. Do not write without approval.
  5. On approval, append the entry below the marker, newest first.
  6. If the decision contradicts an earlier entry, mark the old entry as superseded rather than deleting it.
  7. If the rule is load-bearing for every session, additionally propose a one-line AGENTS.md rule (see reference/memory-policy.md in the kit: decisions live in decisions/; AGENTS.md carries only short rules).

Output artifact

An appended entry in the project's decision log (decisions/*.md or docs/adr/).

Safety constraints

  • Propose, do not overproduce: when in doubt, ask whether it is worth logging.
  • Never write an entry without developer approval of the exact text.
  • Never log secrets, credentials, or personal data.
  • Decision logs are project memory; do not write to the harness's global (user-level) memory.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free