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.
npx skills add YourTechBud/coding-harness-config --skill perform-engineering-guidance-reviewgit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWrote 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.
[](https://agentmods.dev/skills/yourtechbud/coding-harness-config/perform-engineering-guidance-review)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.mddocs/engineering-guidance/core-principles.mddocs/engineering-guidance/how-to-use.mdif 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.
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.
- 8d ago First seen · 115 lines · 31 tokens per session scan A df4adcba397b
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…