agentleFS
tornikebolokadze1-cybertornikebolokadze1-cyber/agent-foundation-kit/.claude/skills/adr/SKILL.md

adr

Skill6 starsChanged 27 days agoMITView on GitHub

Record an architectural decision as docs/adr/ADR-NNNN-slug.md with status proposed — context, options considered, decision, consequences, and how we will confirm it. Use whenever a choice is hard to reverse or shapes several parts of the system (stack, data, hosting, model, channel, security, process), and to replace an accepted decision (supersedes).

97 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fdr, runbook 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.
  • thiagofgfSkill

    fdr

    Use when creating, changing, reviewing, retiring, auditing, or backfilling implemented user-visible feature behavior, permissions, feature-specific rationale, tradeoffs, or relationships to architectural decisions.

    Also in 3 projects that use this

  • AnthropicSkill

    runbook

    Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into exact step-by-step commands, adding troubleshooting and rollback steps to an existing procedure, or writing escalation paths for when things go wrong.

    Also in 5 projects that use this

  • drewdrewthisSkill

    sweep

    Search for similar patterns, anti-patterns, or issues elsewhere in the codebase after a fix or feature. Use after implementing a fix to catch the same bug in other places, or proactively to audit for a known pattern.

    Also in 4 projects that use this

  • vndeeSkill

    product-spec

    Use when starting a new feature, product, or project — before any architecture or code, to define what to build and why

    Also in 3 projects that use this

  • montymiSkill

    tech-spec

    Parse and review Technical Specification documents for completeness, consistency, and implementation readiness

    Also in 3 projects that use this

  • OpenAISkill

    threat-model

    Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 81 edited versions we read keep these.

  • 0

    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. Very specific:

    Does it change an approved spec?: If the decision changes something an approved spec states (a time, a number, a name, a limit), say so in …

    line 27

“Common” is measured: kept by at least 6 in 10 of the 81 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

/adr — record a decision the owner will accept or reject

  1. Is it an ADR? Yes if it is hard to reverse, affects several parts, or someone will later ask "why did we do it this way?". A reversible detail belongs in a plan's ## გადახრები, not an ADR.
  2. Context — intent.md (goals, non-goals), accepted ADRs (docs/adr/README.md), domain facts, bash .claude/hooks/py.sh tools/context_graph.py query <related id>. The stack decision (stage 3) takes its 2–3 options from docs/guides/<kind>.md §2 (kind is in intent.md) and records the stack's five commands — install · run · lint · test · show — with lint and test pointed at the project's own code folder, never the engine's tools/.
  3. Large-scale decision + orchestration enabled? Suggest the architecture loop to the owner: bash .claude/hooks/py.sh orchestration/run.py arch --topic "…" (stage 1: Opus ↔ Sonnet, one round; the owner is asked). Its synthesis.md becomes this ADR's draft.
  4. Write docs/adr/ADR-NNNN-<english-kebab-slug>.md (next free number — docs/adr/README.md names the reserved ones; a project's own ADR has no scope, an engine rule gets scope: engine — ADR-0011), Georgian prose, with frontmatter id, type: adr, title, status: proposed, date, deciders, related (quoted wikilinks), and sections: კონტექსტი · გადაწყვეტილება · განხილული ალტერნატივები (≥2, each with why not) · შედეგები (+ / −) · დადასტურება (prefer a machine check). Copy the shape of docs/adr/ADR-0001-foundation-and-sdlc-loop.md.
  5. Replacing an accepted ADR? Accepted ADRs are immutable (guard G5). Write a new ADR with supersedes: "[[ADR-XXXX-…]]"; when the owner approves it, approve.py marks the old one superseded.
  6. Does it change an approved spec? If the decision changes something an approved spec states (a time, a number, a name, a limit), say so in the chat, reopen the spec (an edit that only sets status: draft), correct every line the decision changes — search the spec for each time, number and name it touches, not only the first — and ask for both approvals; the spec and the ADR must never contradict each other (L-018).
  7. Index — add a row to docs/adr/README.md; run bash .claude/hooks/py.sh tools/context_graph.py check <file>.
  8. Tell the owner in 2–4 Georgian sentences what is being decided and what it costs; the decision is /approve adr NNNN or /approve reject adr NNNN <reason>.

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.