OPOS: Skill for Claude Code

.claude/skills/review-history/SKILL.md

review-history is a skill for Claude Code from Koroqe/OPOS. It costs 45 tokens per session (2,704 once invoked), scanned A, original, MIT.

A scheduled or manual review that examines open proposed changes recorded in history folders and decides how each should be handled.

In plain words
What is it for?
Use it to run weekly triage, inspect the full triage table with dry-run mode, update proposal records, or reconcile the status of upstream pull requests.
Why use it?
It prevents proposed fixes from remaining unresolved by applying small local changes and sending framework-level defects upstream for review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is Koroqe/OPOS's own configuration. It tells Claude Code how to work on OPOS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OPOS configures →

View source ↗ Koroqe/OPOS
Reuse

Borrowing it

Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/review-history/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Koroqe/OPOS

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-history

README.md
[![agentmods](https://agentmods.dev/badge/skills/koroqe/opos/review-history/github.svg)](https://agentmods.dev/skills/koroqe/opos/review-history)
Your own site
<a href="https://agentmods.dev/skills/koroqe/opos/review-history"><img src="https://agentmods.dev/badge/skills/koroqe/opos/review-history/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-history

Your own site · 80×15
<a href="https://agentmods.dev/skills/koroqe/opos/review-history"><img src="https://agentmods.dev/badge/skills/koroqe/opos/review-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,704 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.02704
Opus 5 $0.00023 $0.01352
Sonnet 5 $0.00009 $0.00541
Haiku 4.5 $0.00005 $0.00270

Measured 11d ago against content hash 70f27486f2b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-history scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/review-history/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-history

When to use

As a scheduled routine (registered via /schedule-process review-history, weekly cron 23 7 * * 1 — offset from auto-sync's daily 06:17). Also manually as /review-history, or /review-history --dry_run to print the full triage table without acting on anything.

This skill mechanizes the coo's process-improvement mandate: it is the missing consumer of the proposed_delta signal every process already produces. Before it existed, deltas sat at status: open forever.

Authority mapping

Declared list [commit, push, write_proposal, file_issue, open_pr]:

  • commit — triage edits to STARTER/consumer files within the objective threshold, in-place status/annotation edits to history entries, proposals/LEDGER.md outcome-column updates and rejected-local rows, work-branch create/delete, ff-merge to the default branch, run records.
  • push — pushing the ff-merged default branch, and the proposal branch pushed by an invoked propose-to-core (its outbound write runs inside this run's authority).
  • write_proposal — drafts into the owning agent's dept backlog for above-threshold local deltas.
  • file_issue — consumer-repo issues (closed-unmerged PR reconciliation; propose-to-core fallback issues raised within this run).
  • open_prgh pr create performed by an invoked propose-to-core.

Anything outside this mapping — refuse and record the refusal.

Outbound quoting rule (v0.13)

Nothing under company/resources/ — registry rows, entries, request specs, grant hand-offs — is ever quoted in an upstream-bound artifact; deltas touching resource matters describe the mechanism generically and let propose-to-core's registry-fed blocklist enforce the rest.

Input validation (this skill ingests the least-trusted input in the framework)

  • delta_target: hints read from arbitrary history entries are re-validated before ANY use: repo-relative, no leading /, no .., charset [A-Za-z0-9._/-]. A failing hint is treated as absent (fall back to inference, then to classification); a hint that looks like traversal (../../etc/x) is rejected with a triage note.
  • proposed_delta free text is NEVER interpolated into commands, branch names, or PR titles — slugs are always re-derived by sanitizing file paths to [a-z0-9-].
  • Entry paths must resolve inside the repo root.

Read the full file on GitHub · 88 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 88 lines · 45 tokens per session scan A 70f27486f2b2

Subscribe to this mod's changes

review-history is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 2,704 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

super-evolve

Ultimate self-evolution skill. Merges evolve + self-improve into one comprehensive meta-skill with external research, area focus, dry-run mode, and expanded memory mining.

OZmasterAI/Torus-Framework · 35 tokens

improve-codebase-architecture

A code-review guide for finding places where a codebase's modules are hard to understand, change, or test. It uses the project's terminology and recorded architecture decisions to suggest refactoring opportunities.

Alex-Rachel/TEngine · 69 tokens

grill-with-docs

A code-review skill that uses project decision records and context documents to assess whether a change fits the system's architecture and domain.

Alex-Rachel/TEngine · 71 tokens

compliance-checker

Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…

Affitor/affiliate-skills · 87 tokens

self-improver

Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from…

Affitor/affiliate-skills · 87 tokens

red-team-review

Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.

winstonkoh87/Athena-Public · 65 tokens