Home / chan4lk / specclaw · plugins/specclaw/skills/loop/SKILL.md · GitHub

loop skillB

loop is agent-read markdown (skill) from chan4lk/specclaw: Autonomously iterate build→verify→review until every gate is green or a guardrail halts. Drives the specclaw-loop controller — evaluate gates, reflect, fix the smallest diff, re-verify the whole change, and repeat. Use when asked to loop, iterate until done, or keep fixing until tests pass / verify passes / review is clean. Default-on around /specclaw:build and /specclaw:verify..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# specclaw loop

**First, run** `specclaw-ensure-init .specclaw` — idempotently creates `.specclaw/` if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).

Autonomously drive the change to all-green. The **controller** (`specclaw-loop`) owns every mechanical decision — gate evaluation, signatures, caps, no-progress / regression / oscillation detection, the reward-hack guard, and state/log persistence. This skill only orchestrates the LLM steps: reflect, spawn a fix agent, commit. Follow the controller's JSON verbatim — do not second-guess a `halt`.

## Step 0 — Validate prerequisites

The loop presumes `/specclaw:plan` and at least one `/specclaw:build` pass have already run — it remediates an existing implementation, it does not create one. Confirm the change is built:

```bash
specclaw-validate-change .specclaw <change> verify
```

If it fails (tasks not all complete / no build), tell the user to run `/specclaw:build` first and stop.

Read `loop.enabled` from `.specclaw/config.yaml`:

```bash
grep -A1 '^loop:' .specclaw/config.yaml
```
…

Read the whole file at its exact version.

How to install

Latest version
mdr add chan4lk/specclaw/loop@git:20260918.99e7afb
Exact content
mdr add chan4lk/specclaw/loop@sha256:02151029a1b01a90

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_zxivpugu773uiqa4.svg)](https://markdownregistry.com/a/art_zxivpugu773uiqa4)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260918.99e7afb latest2026-09-18 99e7afb 10,140 BB view · diff
git:20260716.6e3d9c22026-07-16 6e3d9c2 9,505 BB view · diff
git:20260710.13a58542026-07-10 13a5854 9,019 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: Frontmatter declares a name
  • pass: Frontmatter block present
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10140 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

chan4lk/specclaw · 12 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zxivpugu773uiqa4
GET https://markdownregistry.com/api/v1/resolve?ref=chan4lk/specclaw/loop
GET https://markdownregistry.com/api/v1/blob/02151029a1b01a902c1aef27579f79b96e3173a4c4cac70b514ebfd1ff8a55e7

Your agent 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.

More from chan4lk/specclaw

specclaw skill
chan4lk/specclaw · .agents/skills/specclaw/SKILL.md · Run the SpecClaw spec-driven lifecycle in this repository when a request needs proposal, planning, build, verification…
git:20260920.e1dc68c · audit A · 12 stars
CLAUDE.md claude
chan4lk/specclaw · CLAUDE.md
git:20260918.26bbfe4 · audit A · 12 stars
llms-full.txt@docs llmstxt
chan4lk/specclaw · docs/llms-full.txt
git:20260717.fc3814b · audit A · 12 stars
llms.txt@docs llmstxt
chan4lk/specclaw · docs/llms.txt
git:20260717.fc3814b · audit A · 12 stars
CLAUDE.md@plugins/specclaw claude
chan4lk/specclaw · plugins/specclaw/CLAUDE.md
git:20260922.902b03b · audit B · 12 stars
archive skill
chan4lk/specclaw · plugins/specclaw/skills/archive/SKILL.md · Move a completed change to .specclaw/changes/archive/ under its existing name. Closes the GitHub Issue (if sync is…
git:20260918.fdd8978 · audit B · 12 stars
auth-azdo skill
chan4lk/specclaw · plugins/specclaw/skills/auth-azdo/SKILL.md · Interactive setup for Azure DevOps authentication. Prompts for organization, project, and repo, validates a Personal…
git:20260515.4f3e739 · audit B · 12 stars
auth-jira skill
chan4lk/specclaw · plugins/specclaw/skills/auth-jira/SKILL.md · Interactive setup for Jira authentication. Prompts for domain, email, project key, and issue type, validates an…
git:20260515.4f3e739 · audit B · 12 stars
author-spec skill
chan4lk/specclaw · plugins/specclaw/skills/author-spec/SKILL.md · Interactively co-author spec.md for an approved proposal via the spec-author subagent. The agent walks the user through…
git:20260524.1179910 · audit B · 12 stars
auto skill
chan4lk/specclaw · plugins/specclaw/skills/auto/SKILL.md · Run the propose → plan → build → verify lifecycle autonomously across the queue of active changes. Advanced — requires…
git:20260515.d5537a5 · audit B · 12 stars
azdo-issue skill
chan4lk/specclaw · plugins/specclaw/skills/azdo-issue/SKILL.md · Create or update an Azure Boards Work Item that mirrors this proposal. Targets Azure DevOps Boards (Features / User…
git:20260706.ade5fa1 · audit B · 12 stars
bf-analyze skill
chan4lk/specclaw · plugins/specclaw/skills/bf-analyze/SKILL.md · Analyze an existing (possibly legacy) codebase and write a grounded `.specclaw/analysis/codebase-report.md` covering…
git:20260920.62cf3f0 · audit B · 12 stars

Every file in chan4lk/specclaw

Other files named loop

loop skill
qwenlm/qwen-code · packages/core/src/skills/bundled/loop/SKILL.md · Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage -…
git:20260703.0633b8a · audit A · 28,110 stars
loop skill
sethgammon/citadel · skills/loop/SKILL.md · Bounded foreground repetition for the current session. Creates a loop contract, runs or coordinates an action plus…
git:20260611.0f3f8e7 · audit A · 923 stars
loop skill
zaxbyhub/opencode-swarm · .opencode/skills/loop/SKILL.md · Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve…
git:20260904.22a26f7 · audit A · 478 stars
loop skill
mickeyyaya/evolve-loop · skills/loop/SKILL.md · Use when the user invokes /evo:loop or asks to run autonomous improvement cycles, self-evolving development, compound…
git:20260915.76cceb7 · audit A · 5 stars

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