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/hahaxiang27/FlowHarnessWrote 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/hahaxiang27/flowharness/harness.review)<a href="https://agentmods.dev/commands/hahaxiang27/flowharness/harness.review"><img src="https://agentmods.dev/badge/commands/hahaxiang27/flowharness/harness.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/commands/hahaxiang27/flowharness/harness.review"><img src="https://agentmods.dev/badge/commands/hahaxiang27/flowharness/harness.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 | $0.00078 | $0.02419 |
| Opus 5 | $0.00039 | $0.01210 |
| Sonnet 5 | $0.00016 | $0.00484 |
| Haiku 4.5 | $0.00008 | $0.00242 |
Grade A, and why
harness-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 10d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Peer Review
*å ³è peer-reviewer sub-agent · åè§ä¼è®¾è®¡ï¼å·¥ç¨å¸å»ºå¿æºæ¨¡å + ç³»ç»æ?bugï¼ã?
**ä¸ä¸æ管ç?*: ä¿æå½åä¸ä¸æï¼éè¦è¯» diff + CLAUDE.md + specï¼?
æ令
ç¬ç« ad-hoc è·?peer reviewï¼ä¸è¿?evaluator æµç¨ã/harness.exec é»è®¤å?L2.5 å
ç½®åæ ·ç?reviewï¼æ¬å½ä»¤æ¯æ工触åçï¼å¦ï¼è¡¥ review æ?task / review å«äººåç代ç / review è·¨å¤ task çæ´æ®µæ¹å¨ï¼ã?
读å以ä¸æ件ï¼?1. .harness/prompts/peer-reviewer.md â?sub-agent prompt
2. 项ç®æ ?CLAUDE.md â?项ç®å³é
3. specs/<feature>/spec.md â?å½å feature specï¼èªå¨ä» task ID æ¨ææç¨æ·ä¼ åï¼
4. git diffï¼é»è®?HEAD~1..HEADï¼å¯åæ°æå® baseï¼?
è¾å ¥åæ°
- Task IDï¼
$ARGUMENTSï¼å¿ ä¼?· ä¾å¦T042æ?chapter-quiz-genï¼?- Base commitï¼å¯éï¼ï¼--base <SHA>ï¼é»è®?HEAD~1
æ§è¡æ¥éª¤
Step 1 · 解æåæ°
- ä»?task ID åæ¥ specï¼æ«
specs/*/tasks.mdï¼æ¾å°å å«è¯¥ task ID ç?spec - æ¾ä¸å?spec â?è¦åä½ä¸é»æï¼review ä»å¯è·ï¼åªæ¯å°äº spec ä¸ä¸æï¼
- 解æ baseï¼é»è®?
git rev-parse HEAD~1ï¼å¯è¢?--baseè¦ç
Step 2 · æ¶é diff
git diff <base>..HEAD --name-only
git diff <base>..HEAD
å¦æ diff 为空 â?æ¥é并éåºï¼æ²¡æ¹å¨æ²¡ review å¿ è¦ï¼ã?
Step 3 · è°ç¨ peer-reviewer sub-agent
ç?Task å·¥å
· spawn sub-agentï¼?- system promptï¼.harness/prompts/peer-reviewer.md å
¨æ
- åæ°ï¼
task_id+base_commit+ diff å 容
Sub-agent æå
¶ Step 0-5 èµ°å®ï¼åç?.harness/reviews/<task-id>.mdï¼è¾å?PEER_REVIEWER_RESULTã?
Step 4 · ææ¥åè·¯å¾åé¦ç¨æ?
è¾åºæ ¼å¼ï¼?
â?Peer Review å®æ · Task <ID>
æ¥å: .harness/reviews/<task-id>.md
verdict: PASS | WARN | FAIL
score: X/10
must-fix: N · should-fix: M · suggestion: K · sensor-gap: G
è¦ç¹ï¼?ç»äººç?段æè¦ï¼:
- æ¹äºä»ä¹ï¼[Step 1.1 æè¦]
- ææ¥æå¼ï¼[Step 1.4 å¤?2 æ¡]
å®æ´æ¥åæå¼ .harness/reviews/<task-id>.md
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.
- 10d ago First seen · 86 lines · 0 tokens per session scan A 64d9b88db46a
harness-review is a command published in the GitHub repository hahaxiang27/FlowHarness (4 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 2,419 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
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.