independent-review SKILL.md skillA

independent-review from ramboz/jig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ramboz/jig/independent-review@git:20261022.3383e59

Pins git:20261022.3383e59 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ramboz/jig
Path
hosts/copilot/.github/skills/independent-review/SKILL.md
Versions recorded
4
Latest version
git:20261022.3383e59, committed Oct 22, 2026
First version recorded
Sep 16, 2026
Size
19,589 bytes
Repository stars
7
License
MIT

Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without access to the implementation conversation. Use after an implementer subagent completes a spec slice (when the slice is ready for REVIEWED), or after a deviation log is written (for reconciliation review). Do not use for ad-hoc code review unrelated to a spec, or for reviewing a spec's authorship (that's the READY_FOR_REVIEW step in spec-workflow).

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

> **`$JIG_ROOT`** — jig's runtime root (this plugin's own directory).
> Copilot exposes no plugin-root environment variable, so jig's `SessionStart`
> hook publishes the value into session context. In a fresh shell, resolve it
> with the locator:
> `JIG_ROOT="$(for f in "${COPILOT_HOME:-$HOME/.copilot}"/installed-plugins/*/*/.github/scripts/jig_root.py; do [ -f "$f" ] && python3 "$f" && break; done)"`

> **Working posture ([ADR-0056](../../docs/decisions/adr-0056-adversarial-register-quarantine.md)).**
> Adversarial review is a *named, bounded operation.* The skeptical,
> flaw-hunting register this skill builds belongs *inside* the review passes —
> they run in isolated reviewer subagents whose context is discarded. Outside a
> review, default to collaborative and solution-forward; don't carry the
> adversarial stance into ordinary conversation.

> Spec 004 promoted this skill from stub to active. The prompt is constructed
> by `review.py`; Copilot owns the Task invocation.

## What this skill does

Constructs the standardized reviewer-subagent prompt and tells Copilot when /
how to spawn the Task. The skill has four modes, matching the review passes
every slice may run:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ramboz/jig/independent-review@sha256:e45f21ba69d78ada

The line at the top of this page pins the label git:20261022.3383e59, 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_24gxf7sigxorfoj4.svg)](https://markdownregistry.com/a/art_24gxf7sigxorfoj4)

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

Versions

The registry has recorded 4 versions of this file, between Sep 16, 2026 and Oct 22, 2026, about one every 12 days.

versioncommittedcommitsizeaudit
git:20261022.3383e59 latest2026-10-22 3383e59 19,589 BA view · diff
git:20260917.3412c4d2026-09-17 3412c4d 18,297 BA view · diff
git:20260917.3e6faff2026-09-17 3e6faff 17,861 BA view · diff
git:20260916.dc8d4532026-09-16 dc8d453 17,856 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 (19589 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

ramboz/jig · 7 stars · license MIT · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_24gxf7sigxorfoj4
GET https://markdownregistry.com/api/v1/resolve?ref=ramboz/jig/independent-review
GET https://markdownregistry.com/api/v1/blob/e45f21ba69d78adad50322e1027fe6073148ea763a80a69363bf186833946ef8

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 ramboz/jig

AGENTS.md AGENTS.md file
ramboz/jig · AGENTS.md
git:20261004.13a691a · audit A · 7 stars
CLAUDE.md CLAUDE.md file
ramboz/jig · CLAUDE.md
git:20261004.13a691a · audit A · 7 stars
adr-workflow SKILL.md skill
ramboz/jig · hosts/claude/skills/adr-workflow/SKILL.md · Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record…
git:20260805.adc7bb5 · audit A · 7 stars
analyze SKILL.md skill
ramboz/jig · hosts/claude/skills/analyze/SKILL.md · Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW…
git:20260802.96acd90 · audit A · 7 stars
arch-review SKILL.md skill
ramboz/jig · hosts/claude/skills/arch-review/SKILL.md · Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions…
git:20260812.96c2091 · audit A · 7 stars
bug-fix SKILL.md skill
ramboz/jig · hosts/claude/skills/bug-fix/SKILL.md · Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through…
git:20261004.a06c215 · audit A · 7 stars
clarify SKILL.md skill
ramboz/jig · hosts/claude/skills/clarify/SKILL.md · Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized…
git:20261006.e3fb128 · audit A · 7 stars
code-health SKILL.md skill
ramboz/jig · hosts/claude/skills/code-health/SKILL.md · Run a static-analysis pass on a project — detect the ecosystem (Python or Node), drive its linter (ruff / eslint, plus…
git:20260807.8663225 · audit A · 7 stars
contracts SKILL.md skill
ramboz/jig · hosts/claude/skills/contracts/SKILL.md · Team baseline for external-interface contract artifacts: OpenAPI, JSON Schema, AsyncAPI, .proto, and GraphQL SDL, with…
git:20260715.7d538ea · audit A · 7 stars
explain SKILL.md skill
ramboz/jig · hosts/claude/skills/explain/SKILL.md · Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode…
git:20260715.7d538ea · audit A · 7 stars
independent-review SKILL.md skill
ramboz/jig · hosts/claude/skills/independent-review/SKILL.md · Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without…
git:20261022.3383e59 · audit A · 7 stars
memory-sync SKILL.md skill
ramboz/jig · hosts/claude/skills/memory-sync/SKILL.md · Persist new context, terms, learnings, and settled lightweight decisions. Use when the user says remember this, save…
git:20260730.5dea12c · audit A · 7 stars

Every file in ramboz/jig

Other files named independent-review

independent-review SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/independent-review/SKILL.md · Review a code change from a clean context, the way an outside reviewer would. Use after the agent finishes an…
git:20261028.c889a19 · audit A · 495 stars
independent-review SKILL.md skill
benchflow-ai/benchflow · benchmarks/followup-bench/SKILL.md · Incorporate feedback from an independent code reviewer to improve your solution. The reviewer is a different agent that…
git:20260420.eb5b1af · audit A · 359 stars
independent-review SKILL.md skill
karero/croftweaver · skills/independent-review/SKILL.md · Domain-agnostic cross-model review gate: run a planning markdown (PLAN gate) or a branch/PR diff (DIFF gate) through…
git:20261029.4fe5754 · audit A · 9 stars
independent-review SKILL.md skill
lawzava/megapowers · plugins/megapowers/skills/independent-review/SKILL.md · Use when security, auth, billing, concurrency, data integrity, or another high-stakes artifact needs adversarial review…
git:20261102.8206c29 · audit A · 8 stars
independent-review SKILL.md skill
ramboz/jig · hosts/claude/skills/independent-review/SKILL.md · Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without…
git:20261022.3383e59 · audit A · 7 stars
independent-review SKILL.md skill
ramboz/jig · hosts/codex/plugins/jig/skills/independent-review/SKILL.md · Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without…
git:20261022.3383e59 · audit A · 7 stars
independent-review SKILL.md skill
ramboz/jig · skills/independent-review/SKILL.md · Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without…
git:20261022.3383e59 · audit A · 7 stars
independent-review SKILL.md skill
rizwanzafaris/product-manager-os · skills/runtime/independent-review/SKILL.md · Challenge product artifacts for unsupported claims and gate omissions. Use when an independent review must report…
git:20260903.05afd61 · audit A · 4 stars

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