speq-code-guardrails SKILL.md skillA

speq-code-guardrails from marconae/speq-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add marconae/speq-skill/speq-code-guardrails@git:20261011.5b73638

Pins git:20261011.5b73638 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
marconae/speq-skill
Path
.claude/skills/speq-code-guardrails/SKILL.md
Versions recorded
8
Latest version
git:20261011.5b73638, committed Oct 11, 2026
First version recorded
Jul 20, 2026
Size
5,353 bytes
Repository stars
55
License
MIT

TDD cycle and code quality guardrails — failing-test-first, evidence, dependency, error-handling, and test-quality rules. Used by speq implementer and reviewer agents during a speq implement run. Not for general coding.

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

# Code Guardrails

TDD workflow and quality guardrails. Draws on established practice, including work by R. Martin, K. Beck, B. Meyer, and Toyota's Five Whys.

## Golden Rule

**No production code without a failing test first.** Before changing existing code that has no test, add one that captures its current behavior first.

## Evidence Rule

**No claim without evidence.** Run command, show output, then claim.

## Dependency Rule

**No new dependency without confirming the standard library or an already-installed dependency cannot do it first.**

## TDD Cycle (London School)

```
RED    → Write failing test, run it, show failure
GREEN  → Minimal code to pass, run test, show pass
REFACTOR → Clean up, run test + lint, show output
```

Run ONLY the test you created/changed, not the full suite.

## Tests

- Arrange, act, assert. One concept per test.
- The test name states the condition and the expected behavior.
- Independent and repeatable: no shared mutable state, no real clock, network, filesystem, or unseeded randomness.
- Cover every branch and every edge case: empty, single, maximum, off-by-one, transition, and each way the operation can fail.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add marconae/speq-skill/speq-code-guardrails@sha256:0fc90c3e97f572ac

The line at the top of this page pins the label git:20261011.5b73638, 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_je7kc3skw5cx4zgu.svg)](https://markdownregistry.com/a/art_je7kc3skw5cx4zgu)

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

Versions

The registry has recorded 8 versions of this file, between Jul 20, 2026 and Oct 11, 2026, about one every 12 days.

versioncommittedcommitsizeaudit
git:20261011.5b73638 latest2026-10-11 5b73638 5,353 BA view · diff
git:20261003.87999782026-10-03 8799978 5,373 BA view · diff
git:20260925.9f0d8cf2026-09-25 9f0d8cf 5,300 BA view · diff
git:20260825.418db642026-08-25 418db64 5,180 BA view · diff
git:20260825.d3fff942026-08-25 d3fff94 5,220 BA view · diff
git:20260728.e50330f2026-07-28 e50330f 5,237 BA view · diff
git:20260726.540fbff2026-07-26 540fbff 5,115 BA view · diff
git:20260720.15e76d62026-07-20 15e76d6 2,404 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 (5353 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

marconae/speq-skill · 55 stars · license MIT · pushed 2026-10-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_je7kc3skw5cx4zgu
GET https://markdownregistry.com/api/v1/resolve?ref=marconae/speq-skill/speq-code-guardrails
GET https://markdownregistry.com/api/v1/blob/0fc90c3e97f572accf7a8b31a8747c706b8a3c25497a4d6df2f3e8357481fede

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 marconae/speq-skill

speq-adr-rules SKILL.md skill
marconae/speq-skill · .claude/skills/speq-adr-rules/SKILL.md · The rules for when a decision becomes an ADR. The default is no, only durable decisions qualify, search first, one…
git:20261011.5b73638 · audit A · 55 stars
speq-audit SKILL.md skill
marconae/speq-skill · .claude/skills/speq-audit/SKILL.md · Audit a speq project's health — spec-library structure, feature/decision-log/plan validation, ADR noise…
git:20261004.f4ebd5c · audit A · 55 stars
speq-cli SKILL.md skill
marconae/speq-skill · .claude/skills/speq-cli/SKILL.md · Query specs via the speq CLI: feature listing and reading, structure validation, and the absence check. Every speq…
git:20261011.5b73638 · audit A · 55 stars
speq-code-review SKILL.md skill
marconae/speq-skill · .claude/skills/speq-code-review/SKILL.md · Code review tag taxonomy and findings output format — guardrail violations, dead code, test quality, bad comments…
git:20261011.5b73638 · audit A · 55 stars
speq-code-tools SKILL.md skill
marconae/speq-skill · .claude/skills/speq-code-tools/SKILL.md · Semantic code navigation and editing via Serena MCP — symbol-level tools required over grep/find/manual edits. Used by…
git:20261011.5b73638 · audit A · 55 stars
speq-design-philosophy SKILL.md skill
marconae/speq-skill · .claude/skills/speq-design-philosophy/SKILL.md · Complexity-management design principles — deep modules, information hiding and leakage, module boundaries, dependency…
git:20261011.5b73638 · audit A · 55 stars
speq-ext-research SKILL.md skill
marconae/speq-skill · .claude/skills/speq-ext-research/SKILL.md · External documentation and research via Context7 and WebSearch — library APIs and design patterns. Use when current…
git:20261011.5b73638 · audit A · 55 stars
speq-git-discipline SKILL.md skill
marconae/speq-skill · .claude/skills/speq-git-discipline/SKILL.md · Read-only git guardrails. No history writes, verify changes before completing. Used by speq agents during a speq run…
git:20261011.5b73638 · audit A · 55 stars
speq-git-operations SKILL.md skill
marconae/speq-skill · .claude/skills/speq-git-operations/SKILL.md · The git/gh operation-to-command mapping, safety rules, and return formats — invoked directly by the headless…
git:20261004.f4ebd5c · audit A · 55 stars
speq-implement-pr SKILL.md skill
marconae/speq-skill · .claude/skills/speq-implement-pr/SKILL.md · Headless follow-up to /speq-plan-pr. Continues a plan on its feat/plan-name branch and runs it end-to-end: implements…
git:20261011.5b73638 · audit A · 55 stars
speq-implement SKILL.md skill
marconae/speq-skill · .claude/skills/speq-implement/SKILL.md · Orchestrate implementation of a reviewed plan: task breakdown, TDD sub-agents, code review, and verification report…
git:20261004.f4ebd5c · audit A · 55 stars
speq-mission SKILL.md skill
marconae/speq-skill · .claude/skills/speq-mission/SKILL.md · Create or update specs/mission.md and the first specs/architecture.md through a Socratic interview; detects brownfield…
git:20261004.f4ebd5c · audit A · 55 stars

Every file in marconae/speq-skill

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