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.
npx agentmods add agents/akaszubski/autonomous-dev/reviewergit clone --depth 1 https://github.com/akaszubski/autonomous-devWrote 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/akaszubski/autonomous-dev/reviewer)<a href="https://agentmods.dev/agents/akaszubski/autonomous-dev/reviewer"><img src="https://agentmods.dev/badge/agents/akaszubski/autonomous-dev/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 | $0.00016 | $0.04426 |
| Opus 5 | $0.00008 | $0.02213 |
| Sonnet 5 | $0.00003 | $0.00885 |
| Haiku 4.5 | $0.00002 | $0.00443 |
Grade C, and why
reviewer scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Check response status codes (200, 201, etc.) and basic JSON shape with `curl -s URL | python3 -c "import json,sys; json.load(sys.stdin)"` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### API Verification (curl) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 355 lines · 16 tokens per session scan C 847fe0856267
reviewer is an agent published in the GitHub repository akaszubski/autonomous-dev (34 stars, last pushed today), with no licence file. It adds 16 tokens to every session and 4,426 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
ci-formats-reviewer
Reviews SARIF, CodeClimate, Compact, Markdown, and Badge output formats for spec compliance and CI integration correctness.
lsp-reviewer
Reviews LSP server protocol compliance, diagnostic design, code actions, code lens, hover, and editor-agnostic behavior.
lead-validator
Blind validator agent. Receives only raw candidate records + validation rules — no orchestrator state. Computes dedup keys, assigns confidence tiers, flags quarantine candidates, and assigns gdprflag. Does NOT deduplicate (orchestrator's job) and does NOT strip phones (orchestrator's job). Never writes files.
evolve-failure-adjudicator
Reviews an audit rejection from an ARCHITECTURE level and chooses, among the paths deterministic policy has already made legal, which one this cycle should take. Read-only except its own decision artifact.
specwright-reviewer
Code quality and spec compliance reviewer. Verifies implementation matches requirements and project standards. Read-only for source files; Bash restricted to verification commands.
team-privacy-compliance-reviewer
Stage 2 reviewer focused on PII handling, GDPR-style data subject rights, retention, and consent.