better-harness: Skill for Claude Code

.agents/skills/triangulate-spec-review/SKILL.md

triangulate-spec-review is a skill for Claude Code, Codex from QoderAI/better-harness. It costs 70 tokens per session (559 once invoked), scanned A, original, MIT.

A design-document review process that asks several independent AI reviewers to examine the same specification, architecture decision record, or proposal. Their findings are combined and sorted by severity.

In plain words
What is it for?
Use it to review architecture specs, ADRs, plugin proposals, and agent-directory designs, then address shared high-risk findings.
Why use it?
It reduces the chance that one reviewer misses an important problem or overly influences the result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex; mentions Cursor.

This is QoderAI/better-harness's own configuration. It tells Claude Code and Codex how to work on better-harness 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 better-harness configures →

Part of the better-harness plugin — 9 skills shipped together

About the project

Better Harness is an open-source platform for studying and improving how coding agents work on tasks, using written harnesses, controlled tests, and evidence from projects and sessions. Coding teams use it to identify workflow problems and turn them into prioritized improvements and verifiable next steps. Its catalogue entries extend coding-agent workflows for supported hosts such as Claude Code, Codex, Cursor, and others.

QoderAI/better-harness · 2,180 stars · on GitHub · qoderai.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to QoderAI/better-harness. 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/QoderAI/better-harness/main/.agents/skills/triangulate-spec-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/QoderAI/better-harness

Made for: Claude Code, Codex.

Or install better-harness, the plugin that ships this one along with the rest of its 9 skills.

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 triangulate-spec-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/qoderai/better-harness/triangulate-spec-review.svg)](https://agentmods.dev/skills/qoderai/better-harness/triangulate-spec-review)
Your own site
<a href="https://agentmods.dev/skills/qoderai/better-harness/triangulate-spec-review"><img src="https://agentmods.dev/badge/skills/qoderai/better-harness/triangulate-spec-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 559 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00070 $0.00559
Opus 5 $0.00035 $0.00280
Sonnet 5 $0.00014 $0.00112
Haiku 4.5 $0.00007 $0.00056

Measured 9d ago against content hash 15f69c0d9fd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

triangulate-spec-review 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run-triad-review.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/triangulate-spec-review/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triangulate Spec Review

Use independent AI reviewers as an evaluation surface for specs. The lead agent owns synthesis, edits, validation, and the final recommendation.

Workflow

  1. Resolve the target spec path and the acceptance gate. If the user did not name dimensions, default to complexity, convenience, and evolution.
  2. Read the target spec and nearby repo instructions. Do not pass your suspected fixes or conclusions to reviewers.
  3. Use the same read-only prompt for every reviewer. Ask for structured P1/P2/P3 findings and a p1_p2_clear boolean.
  4. Run at least two reviewers; prefer three when available. Use scripts/run-triad-review.mjs for repeatable local runs.
  5. Normalize findings. Treat reviewers as evidence, not authority: fix convergent P1/P2 issues first, challenge weak or contradictory findings, and leave P3 as backlog unless it is cheap and clarifying.
  6. If the user asked for edits, patch only the owning spec or directly related helper docs. Keep unrelated refactors out of the review loop.
  7. Run local validation such as git diff --check, relevant tests, and targeted rg checks for renamed concepts or stale paths.
  8. Repeat the reviewer pass until every requested reviewer reports no P1 or P2, or until the user stops the loop.

Resources

  • Read references/review-loop.md for the prompt contract, severity rubric, command matrix, and iteration patterns.
  • Run this skill's scripts/run-triad-review.mjs --target <path> script, resolved relative to the triangulate-spec-review skill directory, to execute a read-only review round and write normalized JSON output.

Guardrails

  • Pass raw artifacts and task-local context to reviewers, not intended answers.
  • Keep every reviewer prompt materially identical unless a tool requires command syntax changes.
  • Do not let reviewers edit files. The lead agent applies changes after comparing findings.
  • Do not declare acceptance from an average score. Acceptance requires no P1/P2 findings from the required review surface.

Read the full file on GitHub · 48 lines

Files

What ships with it

2 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. 9d ago First seen · 48 lines · 70 tokens per session scan A 15f69c0d9fd4

Subscribe to this mod's changes

triangulate-spec-review is a skill published in the GitHub repository QoderAI/better-harness (2,180 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 559 once invoked, about $0.0003 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 2026-08-30.