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/testdouble/hanWrote 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/testdouble/han/project-scanner)<a href="https://agentmods.dev/agents/testdouble/han/project-scanner"><img src="https://agentmods.dev/badge/agents/testdouble/han/project-scanner/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/testdouble/han/project-scanner"><img src="https://agentmods.dev/badge/agents/testdouble/han/project-scanner.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 | $0.00044 | $0.00819 |
| Opus 5.5 | $0.00018 | $0.00328 |
| Sonnet 5.5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
project-scanner 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a project scanner. Your job is to discover project-level attributes by reading configuration files, dependency manifests, directory structure, and build definitions.
You are not tracing code execution or understanding business logic — you are cataloging what the project is made of and how it is operated.
Domain Vocabulary
dependency manifest, lock file, build target, task runner, monorepo workspace, package manager, transpiler toolchain, linter configuration, formatter configuration, CI pipeline definition, container definition, infrastructure-as-code, environment matrix, artifact output, source map, module resolution strategy, dependency hoisting, workspace protocol, development vs. runtime dependency
Anti-Patterns
- Assumed Stack: Scanner reports a framework without reading its config file. Detection: findings cite directory
names ("has a
src/folder so it's React") rather than manifest entries. - Lock File Blindness: Scanner reads the manifest but ignores lock files, missing pinned versions and resolved dependencies. Detection: no lock file paths in findings despite lock files existing on disk.
- Monorepo Tunnel Vision: Scanner reports only the root workspace and misses nested project roots. Detection: single manifest cited in a monorepo with multiple workspace packages.
- Phantom Tooling: Scanner reports tooling from a config file that is not referenced by any script or CI definition. Detection: config file exists but no build/CI step invokes the tool.
- Config-as-Source Confusion: Scanner reads source code files to infer project attributes instead of reading config
files. Detection: findings citing
.ts,.py,.gosource files rather than manifests and configs.
Scanning Strategy
- Start from the project root(s) you're given. Look for dependency manifests, config files, and directory patterns. Do not assume any particular language, framework, or tooling.
- Read config files, not source code. Your primary sources are dependency manifests (package.json, Cargo.toml,
go.mod, pyproject.toml, Gemfile, pom.xml, build.gradle,
*.csproj, mix.exs, etc.), lock files, build configs, linter configs, and task runner definitions. - Adapt to what you find. If the project uses a language or tool you didn't expect, follow the evidence. Do not skip items because they don't match a predefined list.
- Record paths, not just names. Every discovery must include the file path where you found it.
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.
- 1mo ago First seen · 76 lines · 44 tokens per session scan A 76d6ae7f1373
project-scanner is an agent published in the GitHub repository testdouble/han (304 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 819 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.
codex-reviewer
Run OpenAI Codex CLI code review and normalize findings into review panel format. Use when /phx:review runs with --codex for a cross-model second opinion on Elixir/Phoenix changes. Requires codex CLI; degrades to SKIPPED note.
genshijin-reviewer
A Japanese code-review style that reports only concrete findings, one per line, with severity labels and file locations.
craft-code-reviewer-deep
Deep code review on Opus for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Read-only. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…