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.
git 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/commands/yourtechbud/coding-harness-config/perform-engineering-guidance-review)<a href="https://agentmods.dev/commands/yourtechbud/coding-harness-config/perform-engineering-guidance-review"><img src="https://agentmods.dev/badge/commands/yourtechbud/coding-harness-config/perform-engineering-guidance-review.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02077 |
| Opus 5 | $0.00012 | $0.01038 |
| Sonnet 5 | $0.00005 | $0.00415 |
| Haiku 4.5 | $0.00002 | $0.00208 |
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 — 113 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 · 113 lines · 24 tokens per session scan A 576f1f57d13b
perform-engineering-guidance-review is a command published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 2,077 once invoked, about $0.0001 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 commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.