agentleFS
Sign inStart free
arbelharbelh/perdure/skills/decisions/SKILL.md

decisions

Skill0 starsChanged 28 days agoMITView on GitHub

List architectural decision records (ADRs). Shows active decisions by

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use adr-verbatim, file-tree and 4 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.
  • davidondrejSkill

    adr-verbatim

    Record concise ADRs that preserve the user''s decisions without conversational noise. Use for "adr-verbatim", "new ADR", "document that as an ADR", "record this decision", or supplied ADR wording.

    Also in 3 projects that use this

  • davidondrejSkill

    file-tree

    Manually-invoked skill that prints a nice file tree of the current topic in a code block. Use when the user says "file-tree" or "file tree".

    Also in 3 projects that use this

  • attentiondotnetSkill

    setup-help

    Walk the user through setting up anything step by step. Use when the user asks for help setting up, configuring, installing, or getting something working — "help me set up X", "walk me through this", "setup-help". Differentiator: gives one current step at a time, then always lists every remaining setup step after each response.

    Also in 3 projects that use this

  • itgoyoSkill

    browser-harness

    Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

    Also in 3 projects that use this

  • +2 more from davidondrej

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-only by default; --reindex is the one action that writes (it rebuilds INDEX.md only — never the ADR files themselves).

    line 12
  2. Very specific:

    Read perdure/decisions/INDEX.md and parse its status sections.

    line 34
  3. Very specific:

    Never modify ADR files; --reindex rewrites INDEX.md only, diff shown first

    line 65
  4. Distinctive:

    Never suppress a detected INDEX/file mismatch

    line 66
  5. Distinctive:

    If an ADR can't be read, log and continue

    line 68

“Common” is measured: kept by at least 6 in 10 of the 10 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

List Architecture Decision Records

Read-only by default; --reindex is the one action that writes (it rebuilds INDEX.md only — never the ADR files themselves). The ADR schema is defined in docs/RECORDS-CONVENTION.md (also at references/RECORDS-CONVENTION.md beside this SKILL.md in a skills-CLI install).

Arguments

FlagEffect
(none)Show Active ADRs (what's in force now)
--allShow every status section, PLUS decisions recorded in workflow files' # Decisions sections (with {promote} candidates flagged)
--reindexRebuild perdure/decisions/INDEX.md from the ADR files' frontmatter
--tag <name> / --workflow <slug> / --status <name>Filters

Steps

1. Verify prerequisites

ADRs live at perdure/decisions/. If no ADR directory exists, report "No decisions recorded yet. Create one: /perdure:decide <slug>" and exit gracefully.

2. Read

Read perdure/decisions/INDEX.md and parse its status sections. If the INDEX is missing, or an ADR you touch contradicts its INDEX section, say so and offer --reindex (don't rebuild without being asked).

3. --reindex (when requested)

  1. Scan every perdure/decisions/*.md except INDEX.md; parse frontmatter (id, title, status, date, tags, superseded-by).
  2. Validate: 3-digit id, status ∈ proposed/accepted/superseded/deprecated/rejected, non-empty title. Report malformed files; skip them.
  3. Rewrite INDEX.md grouped by status (Active = proposed+accepted), newest first, one table row per ADR linking to its file. Show the diff before writing.

4. --all — include workflow decisions

Scan perdure/workflows/*.md files' # Decisions sections. Show them grouped by workflow with status, after the ADR sections. Flag entries marked {promote} as promotion candidates (/perdure:decide <slug> promotes; /perdure:close promotes at close per the auto-promote-decisions preference: under the default heuristic, marked decisions always, plus unmarked ones that pass the inheritance test). Skip entries already marked [promoted → #NNN].

5. Output

Plain markdown tables — ID, title, date, tags per row — one section per status shown, then a one-line total (N active, N superseded, …). To read a specific ADR: cat perdure/decisions/<filename>.

Safety rules

  • Never modify ADR files; --reindex rewrites INDEX.md only, diff shown first
  • Never suppress a detected INDEX/file mismatch
  • Work offline — no network calls
  • If an ADR can't be read, log and continue

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