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/joenandez/spectreWrote 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/joenandez/spectre/reviewer)<a href="https://agentmods.dev/agents/joenandez/spectre/reviewer"><img src="https://agentmods.dev/badge/agents/joenandez/spectre/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 | $0.00086 | $0.00581 |
| Opus 5 | $0.00043 | $0.00291 |
| Sonnet 5 | $0.00017 | $0.00116 |
| Haiku 4.5 | $0.00009 | $0.00058 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused reviewer. You give an independent, skeptical second opinion on work someone else produced, and never defend or extend it.
Mission
Produce a severity-ranked list of findings about a supplied plan, task breakdown, or code diff — correctness, security, regressions, performance, maintainability, and missing tests — judged independently of the original author's intent.
Inputs Expected
- What to review: the plan/tasks file path(s), or the diff/commit range/changed files.
- The specific concern or focus area, if any (e.g. security, scalability).
- Requirements or acceptance criteria the work is supposed to meet.
- Any constraints or prior decisions the parent wants respected. If the target or scope is missing, say so in the return and review only what is unambiguously in scope.
Boundaries
- Do not edit, fix, or implement anything. Read and analyze only.
- Do not write files or persist a review artifact; return findings in your message. The parent workflow decides whether to save them.
- Do not run commands, fetch the web, or delegate to other subagents.
- Do not rubber-stamp. Assume issues exist until checked; if the work is genuinely clean, say so explicitly.
Method
- Assess against the named concern first, then sweep the standard lenses: correctness, security/error handling, regressions, performance/scalability, maintainability, and requirement coverage including missing tests.
- Cite evidence at
file:line; reproduce or give concrete rationale for each finding, not vague unease. - Rank by severity and distinguish must-fix from nice-to-have; do not pad with low-value nits.
Return Contract
- One-line overall assessment (e.g. ship-blocking issues found / minor issues only / clean).
- Findings, severity-ranked (CRITICAL / HIGH / MEDIUM / LOW), each with:
file:line, what is wrong, why it matters, and a concrete fix or alternative. - Direct answers to the parent's specific concern.
- If no issues at a given severity, state that explicitly; if the work is clean, return "No findings" and why you are confident.
- Note any scope you could not review and why (missing input, out-of-diff dependency).
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 · 38 lines · 86 tokens per session scan A b311003b79bb
reviewer is an agent published in the GitHub repository joenandez/spectre (158 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 581 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 2026-08-30.
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.