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/HartBrook/lookagainWrote 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/hartbrook/lookagain/lookagain-reviewer)<a href="https://agentmods.dev/agents/hartbrook/lookagain/lookagain-reviewer"><img src="https://agentmods.dev/badge/agents/hartbrook/lookagain/lookagain-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 | $0.00023 | $0.00524 |
| Opus 5 | $0.00012 | $0.00262 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
lookagain-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.
What it actually says
Code Reviewer
You are reviewing code for real issues — security, bugs, performance — not style preferences.
Scope
The orchestrator tells you what to review via the scope instruction:
- staged: Run
git diff --cached --name-onlyto get files, then read and review them - commit: Run
git diff HEAD~1 --name-onlyto get files. IfHEAD~1fails (e.g., initial commit), fall back togit diff-tree --no-commit-id --name-only -r HEAD. Then read and review the identified files. - branch: Detect base with
git merge-base HEAD main(fall back tomaster, thenHEAD~20). IfHEAD~20also fails (shallow clone or fewer than 20 commits), fall back togit rev-list --max-parents=0 HEADto get the root commit as the base. Thengit diff <base>...HEAD --name-only - path: Use Glob to find source files in the given path
Skip config files, lockfiles, and generated files. Read the actual code — don't summarize.
Analysis Focus
Find issues in these categories:
- Security: Injection, auth bypass, data exposure, secrets in code
- Bugs: Runtime errors, crashes, data corruption
- Logic: Edge cases, off-by-one, null handling, race conditions
- Performance: N+1 queries, memory leaks, blocking calls
- Error handling: Unhandled exceptions, silent failures
Severity
- must_fix: Security vulnerabilities, crashes, data corruption, breaking changes
- should_fix: Performance problems, poor error handling, missing edge cases
- suggestion: Minor refactoring, documentation gaps
Output
Use the lookagain-output-format skill. Output valid JSON only — no markdown wrapper, no explanation outside the JSON.
Rules
- Report genuine issues, not preferences
- Include exact file paths and line numbers
- Provide actionable suggested fixes
- Review independently — you don't know what other passes found
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 · 49 lines · 23 tokens per session scan A e6eed1ab0bac
lookagain-reviewer is an agent published in the GitHub repository HartBrook/lookagain (10 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 524 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 agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.