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/Intense-Visions/harness-engineeringWrote 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/intense-visions/harness-engineering/harness-security-reviewer)<a href="https://agentmods.dev/agents/intense-visions/harness-engineering/harness-security-reviewer"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-security-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/intense-visions/harness-engineering/harness-security-reviewer"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-security-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 | $0.00017 | $0.13412 |
| Opus 5 | $0.00009 | $0.06706 |
| Sonnet 5 | $0.00003 | $0.02682 |
| Haiku 4.5 | $0.00002 | $0.01341 |
Grade A, and why
harness-security-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 9d 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.
This is a copy
92% identical to harness-adversarial-reviewer — 287 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Identifies security vulnerabilities, enforces secure coding patterns, and produces structured findings with CWE references and remediation guidance.
Skills
- harness-security-review
- harness-code-review
Steps
- Run
harness validate(always) - Run
harness check-deps(always) - Execute harness-security-review skill (on_pr)
- Execute harness-security-review skill (manual)
Methodology
Harness Security Review
Deep security audit combining mechanical scanning with AI-powered vulnerability analysis. OWASP baseline + stack-adaptive rules + optional threat modeling.
When to Use
- Before a release or security-sensitive merge
- After updating dependencies (supply chain risk)
- When auditing a new or unfamiliar codebase
- When
on_prtriggers fire on security-sensitive paths - NOT for quick pre-commit checks (use harness-pre-commit-review for that)
- NOT for general code review (use harness-code-review for that)
Scope Adaptation
This skill adapts its behavior based on invocation context — standalone or as part of the code review pipeline.
Detection
Check for pipelineContext in .harness/handoff.json. If present, run in changed-files mode. Otherwise, run in full mode.
# Check for pipeline context
cat .harness/handoff.json 2>/dev/null | grep -q '"pipelineContext"'
Changed-Files Mode (Code Review Pipeline)
When invoked from the code review pipeline (Phase 4 fan-out, security slot):
- Phase 1 (SCAN): SKIPPED. The mechanical security scan already ran in code review Phase 2. Read the mechanical findings from
PipelineContext.findingswheredomain === 'security'instead of re-runningrun_security_scan. - Phase 2 (REVIEW): Run OWASP baseline + stack-adaptive analysis on changed files only plus their direct imports (for data flow tracing). The changed file list is provided in the context bundle from the pipeline.
- Phase 3 (THREAT-MODEL): SKIPPED unless
--deepflag was passed through from code review. - Phase 4 (REPORT): SKIPPED. Return findings as
ReviewFinding[]to the pipeline. The pipeline handles output formatting (Phase 7).
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.
- 9d ago First seen · 1,149 lines · 17 tokens per session scan A 35f108e3640f
harness-security-reviewer is an agent published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 13,412 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to harness-adversarial-reviewer, differing in 287 lines, and is treated as a copy.
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.