spec-loop SKILL.md skillA

spec-loop from martinffx/atelier is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add martinffx/atelier/spec-loop@git:20261018.7301061

Pins git:20261018.7301061 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
martinffx/atelier
Path
skills/spec-loop/SKILL.md
Versions recorded
4
Latest version
git:20261018.368afab, committed Oct 18, 2026
First version recorded
Oct 18, 2026
Size
4,414 bytes
Repository stars
48
License
MIT

Run an approved Spec-backed Plan (design.md and plan.json both present) unattended to a draft PR: implement and review each batch with fresh subagents, commit, then finish with one whole-branch review. Use when the user says "run it to the end" or "implement everything and open a PR".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Spec Loop

Drive an approved Spec-backed Plan to a draft PR without stopping for the human. The main agent
only drives; fresh subagents implement and review. Never run `code-review rs` in this loop.

**Announce at start:** "I'm using the spec-loop skill to run this plan to a draft PR."

This skill makes no design decisions. A finding or blocker that needs a plan change goes back to
`spec-plan`; a design change goes back to `spec-brainstorm`.

## Start

Runs on every invocation, including a resume.

1. If `design.md` or `plan.json` is missing, stop and use spec-implement. Otherwise follow
   **spec-implement** Prerequisites and "Load and Review the Plan" while the human is present.
2. Stop if the tree is dirty or the test suite is not green.
3. Ask one authorization question naming each action. The answer is the explicit authorization
   **code-commit** and **code-pull-request** require.
   - commit after every batch and after the final fix
   - push to `<remote>/<branch>`, without force
   - open a **draft** PR with code-pull-request's Create flow
   - budget: at most N batches (plan task count / 3, rounded up, plus 1); stop when the same task
     or test fails twice
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add martinffx/atelier/spec-loop@sha256:9874d225914e51f1

The line at the top of this page pins the label git:20261018.7301061, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ng6hext3y55cyqbe.svg)](https://markdownregistry.com/a/art_ng6hext3y55cyqbe)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, all committed on Oct 18, 2026.

versioncommittedcommitsizeaudit
git:20261018.368afab latest2026-10-18 368afab 4,414 BA view · diff
git:20261018.73010612026-10-18 7301061 4,561 BA view · diff
git:20261018.9919f552026-10-18 9919f55 4,511 BA view · diff
git:20261018.ed671a92026-10-18 ed671a9 4,848 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4414 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

martinffx/atelier · 48 stars · license MIT · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ng6hext3y55cyqbe
GET https://markdownregistry.com/api/v1/resolve?ref=martinffx/atelier/spec-loop
GET https://markdownregistry.com/api/v1/blob/9874d225914e51f199a58ef6e457a806456a261ae5d5c05e8738689e1a3c5072

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from martinffx/atelier

AGENTS.md AGENTS.md file
martinffx/atelier · AGENTS.md
git:20261017.81dd276 · audit A · 48 stars
atelier-orchestrator SKILL.md skill
martinffx/atelier · skills/atelier-orchestrator/SKILL.md · Skill routing and workflow orchestration. Selects Inline Plan or Spec-backed Plan, routes to the correct workflow…
git:20261018.9919f55 · audit A · 48 stars
atelier-setup SKILL.md skill
martinffx/atelier · skills/atelier-setup/SKILL.md · Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance…
git:20260801.96f6fe8 · audit A · 48 stars
code-commit SKILL.md skill
martinffx/atelier · skills/code-commit/SKILL.md · Generate and validate conventional commit messages following the conventionalcommits.org spec. Use whenever the user…
git:20260801.96f6fe8 · audit A · 48 stars
code-handoff SKILL.md skill
martinffx/atelier · skills/code-handoff/SKILL.md · Compact the current conversation into a handoff document for another agent to pick up.
git:20260718.abd6ec9 · audit A · 48 stars
code-pull-request SKILL.md skill
martinffx/atelier · skills/code-pull-request/SKILL.md · Manage GitHub pull requests or GitLab merge requests: create, read/leave/respond to comments, and merge. Triggers on…
git:20260717.53e8957 · audit A · 48 stars
code-review SKILL.md skill
martinffx/atelier · skills/code-review/SKILL.md · Multi-agent code review run as a debate. Critics raise findings in parallel, an Author defends the change, Critics…
git:20261018.a370713 · audit A · 48 stars
code-subagents SKILL.md skill
martinffx/atelier · skills/code-subagents/SKILL.md · Implementation subagent dispatch patterns. Use when a task's design is settled and the file just needs to be made, or…
git:20261018.368afab · audit A · 48 stars
oracle-codebase-design SKILL.md skill
martinffx/atelier · skills/oracle-codebase-design/SKILL.md · Shared vocabulary and principles for designing deep modules. Use when designing or changing a module's interface…
git:20261009.3672e9c · audit A · 48 stars
oracle-debug SKILL.md skill
martinffx/atelier · skills/oracle-debug/SKILL.md · Disciplined debugging methodology. Triggers on bug reports, test failures, "debug this", "diagnose this", unexpected…
git:20261009.3672e9c · audit A · 48 stars
oracle-domain-modelling SKILL.md skill
martinffx/atelier · skills/oracle-domain-modelling/SKILL.md · Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous…
git:20260801.96f6fe8 · audit A · 48 stars
oracle-grill-me SKILL.md skill
martinffx/atelier · skills/oracle-grill-me/SKILL.md · Grill the user relentlessly about a plan, decision, or idea, maintaining the project's domain model (CONTEXT.md, ADRs)…
git:20261009.3672e9c · audit A · 48 stars

Every file in martinffx/atelier

Other files named spec-loop

spec-loop SKILL.md skill
kamioj/spec-workflow · codex/skills/spec-loop/SKILL.md · Goal-driven autonomous round loop. Give it a goal + acceptance checklist + round budget (touchpoint 1), then it…
git:20260910.a57f970 · audit A · 20 stars

Browse by kind, by grade A, or by owner.