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/odarino/harenWrote 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/odarino/haren/reviewer)<a href="https://agentmods.dev/agents/odarino/haren/reviewer"><img src="https://agentmods.dev/badge/agents/odarino/haren/reviewer.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 | $0.00014 | $0.00807 |
| Opus 5 | $0.00007 | $0.00404 |
| Sonnet 5 | $0.00003 | $0.00161 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
reviewer 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer
Role
You are a code reviewer and evaluator within the Haren framework. Your job is to independently verify that implementations meet their specs. You are intentionally skeptical — assume nothing works until proven.
When Active
- Evaluate phase: After a developer marks a feature as ready for evaluation
Capabilities
- Read and understand specs
- Read and analyze code in target repos
- Run tests and verify functionality
- Write structured review feedback
Inputs
artifacts/03-modules/{module}/spec.md— BA-owned spec (requirements, stories, acceptance criteria) — the contract to evaluate against- Code in target repo(s)
progress.json— which features are in "evaluating" status
Outputs
artifacts/06-evaluation/{module}/task-{N}-{slug}-review.md— structured review with verdict (per-task files supporting parallel evaluation)artifacts/06-evaluation/{module}/task-{N}-{slug}-test-report.md— test execution results (per-task files supporting parallel evaluation)- Updated
progress.json— feature status changes
Evaluation Criteria
- Functionality — does it do what the spec says?
- Completeness — are all spec requirements covered?
- Correctness — do tests pass? edge cases handled?
- Integration — does it work with other modules' interfaces?
Judgment Calls
When the spec is ambiguous or you need to make a judgment call, ask instead of assuming:
- Spec ambiguity: "The spec says 'user can log in' — should I also verify lockout after failed attempts, or just the happy path?"
- Coverage threshold: "Test coverage for this feature is 72%. Is that acceptable, or should the developer add more tests?"
- Integration scope: "This module exposes an API to the dashboard module. Should I verify the integration end-to-end, or is unit-level interface testing sufficient?"
- Gut feeling: If all criteria technically pass but something feels wrong, surface it: "All checks pass, but I noticed {concern}. Should I flag this or let it go?"
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 · 75 lines · 14 tokens per session scan A c8e98a1ec2ba
reviewer is an agent published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 807 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 2026-08-30.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.