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 agentmods add commands/yourtechbud/coding-harness-config/create-review-guidegit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWhat 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 | $0.00018 | $0.00796 |
| Opus 5 | $0.00009 | $0.00398 |
| Sonnet 5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
create-review-guide 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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You generate a reviewer's orientation guide for a code change, so a human can review a large diff efficiently. This is a navigation aid, not a quality review — it does not judge or approve the code; it helps the reviewer build a mental model and know where to look.
Change scope
User-supplied scope:
$ARGUMENTS
If no user-supplied scope is provided, default to the current working tree changes
relative to HEAD, including staged, unstaged, and untracked files.
Goal
Produce a single self-contained HTML file under scratch/review/ that orients a
reviewer across two layers. Name the file after what the change is about, using a
short descriptive kebab-case slug (e.g. scratch/review/auth-token-refresh.html)
rather than a fixed name, so each guide is distinct and earlier guides are not
clobbered.
The guide covers two layers:
- Orientation — what this change is trying to achieve, and what a reviewer should therefore expect to change.
- Review walk — a module-by-module walk through the change. Start with a reading path overview: the affected modules in recommended reading order, each with a one-line reason. Then, for each module in that order, give its breakdown (expected logic, what is non-obvious or risky, what to verify) together with its files and focused notes on what to look at in each. End with a "Loose ends & miscellaneous" bucket for changed files that don't belong to a clean module (config, lockfiles, stray tweaks), so every changed file is still covered.
Success criteria
- A reviewer can build a mental model before reading any code, then read code to check whether it matches expectations.
- Logic is framed as expectations to test against the code, not conclusions to trust.
- Risky or non-obvious spots are called out with what to verify.
- It reads easily: plain, friendly language and short sentences, with repo jargon or technical terms defined briefly the first time they appear.
- The page is light and easy on the eyes, not a wall of text.
- A clear reading path is recommended; files live inside the module they belong to; every changed file is covered, including loose ends.
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.
- 2d ago First seen · 74 lines · 18 tokens per session scan A 47561dbb4cbd
create-review-guide is a command published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 18 tokens to every session and 796 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.