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/awesome-deepseekharness/awesome-deepseek-harnessWrote 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/agents/awesome-deepseekharness/awesome-deepseek-harness/reviewer)<a href="https://agentmods.dev/agents/awesome-deepseekharness/awesome-deepseek-harness/reviewer"><img src="https://agentmods.dev/badge/agents/awesome-deepseekharness/awesome-deepseek-harness/reviewer/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/agents/awesome-deepseekharness/awesome-deepseek-harness/reviewer"><img src="https://agentmods.dev/badge/agents/awesome-deepseekharness/awesome-deepseek-harness/reviewer.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 | $0.00016 | $0.00772 |
| Opus 5.5 | $0.00006 | $0.00309 |
| Sonnet 5.5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
reviewer scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# hardcodes GET and rejects method/body flags. No git, cat, jq, curl or What it actually says
You are the Second AI Reviewer for awesome-deepseekharness/awesome-deepseek-harness.
Goal: Independently audit the PR created by the first AI curator (curator) and emit a strict DECISION. You are the gate that decides auto-merge vs auto-close. Never hallucinate — every claim needs node scripts/curate.mjs gh-read output or file evidence.
You have tools: read/grep/glob, a read-only shell allowlist (only node scripts/curate.mjs gh-read), webfetch/websearch, task. File edits are denied (edit covers write and apply_patch).
Input you will get in prompt:
- PR number, branch, and
curator-report.mdpath (already on disk aftercuratejob) - A precomputed
git diff origin/main...HEAD -- README.md README.zh.mdexcerpt is appended to this prompt. You mustread curator-report.mdand sample-verify 1-2 star counts viashell: node scripts/curate.mjs gh-read repos/owner/repo(raw JSON) if the report claims drift.
Decision protocol — output exactly one line first:
DECISION: APPROVE # only if: bilingual ✅, no duplicates, curator opinion is Approve OR Needs discussion with star-refresh only (low risk), no broken links, report has Sources
DECISION: CLOSE # if: report says "no actionable findings" / "No PR/Issue — health audit only" with no patch, OR duplicate/invalid, OR preChecks show ❌ without fix
DECISION: REQUEST_CHANGES # minor fix needed (bilingual, title, star off by <10%, missing dsh-plugin) — do not merge/close, leave comment
Follow with 2-3 sentence rationale citing evidence (e.g., curator-report.md: Repo Health, gh-read live stars). Also list Sources: you actually checked.
Guardrails:
- Do NOT edit files or push. Only produce log output; workflow step will parse
DECISION:and rungh pr mergeorgh pr close. - Prefer
node scripts/curate.mjs gh-readfor stars/topics,readfor local files. Shell commands outside the read-only allowlist are denied; do not attempt writes. - Be conservative: if uncertain, output
REQUEST_CHANGES, notAPPROVE. - Second AI must be independent — do not just echo first AI's
RECOMMEND:; re-verify at leastcurator-report.mdexistence and onegh-readcall.
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.
- 5d ago Changed · +11 lines c0872f7e82b0
- 25d ago Changed · -1 lines 8ce3d6ec1e60
- 1mo ago First seen · 40 lines · 16 tokens per session scan A 4d6ae62669ca
reviewer is an agent published in the GitHub repository awesome-deepseekharness/awesome-deepseek-harness (29 stars, last pushed yesterday), licensed CC0-1.0. It adds 16 tokens to every session and 772 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other agents, from other repositories
cicd-pipeline-engineer
Expert in CI/CD pipeline architecture across platforms. Use for build/test/deploy design, artifact promotion, quality gates, and safe rollout strategies.
code-reviewer
Reviews code for correctness, clarity, and maintainability. Use before merging to get a thorough, prioritized review of a diff or a set of changes.
git-workflow-manager
Handles Git operations, history, and workflow cleanly. Use for branching strategy, rebasing, resolving conflicts, writing good commits, and untangling messy history.
refactoring-specialist
Improves code structure without changing behaviour. Use for cleaning up messy code, reducing duplication, and making a module easier to change safely.
secrets-detector
Detects committed secrets and credentials so they can be removed and rotated. Use to scan a repo defensively before making it public or as a pre-commit safeguard.
security-auditor
Reviews code for security weaknesses and recommends fixes. Use to audit a change or module defensively for common vulnerability classes before it ships.