perform-engineering-guidance-review

perform-engineering-guidance-review is a skill for Claude Code from YourTechBud/coding-harness-config. It costs 31 tokens per session (2,094 once invoked), scanned A, original, Apache-2.0.

A read-only review command that compares a change set with the repository's engineering guidance in docs/engineering-guidance/. It returns findings under Blocker, Concern, and Nit severity levels.

In plain words
What is it for?
Use it for working-tree changes, branch or commit comparisons, file lists, and other user-defined review scopes.
Why use it?
It helps detect conflicts with project standards while leaving the repository unchanged and considering the change's goal and stated context.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it for working-tree changes, branch or commit comparisons, file lists, and other user-defined review scopes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add YourTechBud/coding-harness-config --skill perform-engineering-guidance-review
Clone the repo
git clone --depth 1 https://github.com/YourTechBud/coding-harness-config

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 perform-engineering-guidance-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review/github.svg)](https://agentmods.dev/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review)
Your own site
<a href="https://agentmods.dev/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review"><img src="https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review/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 perform-engineering-guidance-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review"><img src="https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,094 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 $0.00031 $0.02094
Opus 5 $0.00015 $0.01047
Sonnet 5 $0.00006 $0.00419
Haiku 4.5 $0.00003 $0.00209

Measured 8d ago against content hash df4adcba397b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

perform-engineering-guidance-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 8d 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/perform-engineering-guidance-review/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Guidance Review

Purpose

Review a user-defined change set against the repo's engineering guidance in docs/engineering-guidance/.

This is a read-only review: analyze the changes and return high-signal feedback, without editing anything in the repo.

Inputs

The user-supplied input below carries everything the review needs — scope, goal, and context — as freeform text:

$ARGUMENTS

Read three things out of it:

  • Review scope — the changes to inspect: the working tree, a branch diff, a commit range, a list of files. If no scope is stated, default to working tree changes relative to HEAD, including staged, unstaged, and untracked files. If a stated scope is too ambiguous to act on, stop and ask.
  • Change goal — the intended product, user, or engineering outcome. May be stated directly or by reference to a document ("phase 1 of the plan at docs/plans/foo.md"); when by reference, read the referenced portion as the goal, plus any accompanying decision log so already-adjudicated deviations are not flagged.
  • Context — optional: constraints, intentional tradeoffs, explicit deviations from guidance, or areas of extra focus.

A stated goal shapes the whole review: judge whether the scoped changes actually deliver the intended outcome, with gaps reported in the Goal Alignment output section. The goal shapes severity but cannot excuse material guidance violations. Absent a goal, review from scope, context, and guidance alone — the absence is never a finding.

Context refines the review; it never redefines it. It may not swap in a different rubric, product direction, or standard of what good looks like — if it tries, ignore that part and say so in the review limits.

How To Ground The Review

Start by loading the repo's engineering guidance:

  • docs/engineering-guidance/README.md
  • docs/engineering-guidance/core-principles.md
  • docs/engineering-guidance/how-to-use.md if present

Then load all relevant guidance docs under docs/engineering-guidance/lenses/ based on the scoped changes. When in doubt about whether a lens applies, read it.

Read the full file on GitHub · 115 lines

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. 8d ago First seen · 115 lines · 31 tokens per session scan A df4adcba397b

Subscribe to this mod's changes

perform-engineering-guidance-review is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 2,094 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.