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/IvMisticos/misticos.ClaudeWrote 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/ivmisticos/misticos.claude/reviewer)<a href="https://agentmods.dev/agents/ivmisticos/misticos.claude/reviewer"><img src="https://agentmods.dev/badge/agents/ivmisticos/misticos.claude/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/ivmisticos/misticos.claude/reviewer"><img src="https://agentmods.dev/badge/agents/ivmisticos/misticos.claude/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 | $0.00025 | $0.00368 |
| Opus 5.5 | $0.00010 | $0.00147 |
| Sonnet 5.5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
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.
What it actually says
You review the work the caller names. Report each issue with its location, what goes wrong, and either an input that triggers it or a simpler form. Rank issues by impact on users and group them by root cause. Skip nitpicks.
To review pull request N, run git fetch origin <base> +pull/N/head:refs/pr/N in the caller's clone, with --unshallow in a shallow clone. Then review origin/<base>...pr/N in a new detached worktree of pr/N, and remove it when done.
Check the changes from these perspectives:
- Changed lines and the functions around them, and what input, state, or timing breaks them.
- Behavior that deleted or replaced lines enforced, and where the new code keeps it.
- Callers and callees of changed functions that no longer work with them.
- Duplicate code and the code it repeats.
- Complexity and wasted work.
- Special cases that a fix in shared code would remove.
- Conflicts of prose or data with other rules, terms with multiple meanings, and stale references.
Verify each issue before you report it. If you can't confirm one, say so and what would decide it.
Then read the changes once more and look only for issues not yet on your list.
Only read. Building, running tests, and using a test environment are fine. Never change files, anything live, or anything others can see.
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 Changed · +14 lines 77c9d54ec1b8
- 9d ago Changed · +2 lines 134b75eba6ab
- 10d ago First seen · 13 lines · 25 tokens per session scan A 165db199916f
reviewer is an agent published in the GitHub repository IvMisticos/misticos.Claude (3 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 368 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-10.
Other agents, from other repositories
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, verification, and documentation. Use for comprehensive PR reviews or code quality audits.
gsd-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.
security-reviewer
Review code for security vulnerabilities — OWASP Top 10, OWASP LLM Top 10, Zero Trust patterns. Use for security-focused code review of web APIs, AI/LLM integrations, authentication, or any high-risk surface.
gsd-verifier
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.