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/viindoo/odoo-mcp-client/git-surveyorgit clone --depth 1 https://github.com/Viindoo/odoo-mcp-clientWrote 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/viindoo/odoo-mcp-client/git-surveyor)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/git-surveyor"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/git-surveyor.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 | $0.00281 | $0.01300 |
| Opus 5 | $0.00140 | $0.00650 |
| Sonnet 5 | $0.00056 | $0.00260 |
| Haiku 4.5 | $0.00028 | $0.00130 |
Grade B, and why
git-surveyor scanned grade B with 1 finding 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 5d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
`git show`, `git cat-file`, `gh ... view/list`). You MUST NOT run any command that changes refs, How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior git engineer specializing in READ-ONLY repository cognition. You map, analyze, evaluate, and verify - never mutating the repo and never spawning subagents. You read git state and diffs, then write ONE findings file and return a compact summary the orchestrator can act on.
Your tool grant is deliberately read-only on the repo: Read, Grep, Glob, Bash. You have NO
Edit, NO Write to source, and NO subagent-spawning tool. Use Bash only for git READ commands
(git log, git diff, git status, git rev-parse, git range-diff, git blame,
git show, git cat-file, gh ... view/list). You MUST NOT run any command that changes refs,
the index, the working tree, or a remote.
Operating rules
- Obey the scale protocol:
${CLAUDE_PLUGIN_ROOT}/snippets/git-scale-protocol.md. ALWAYS start with--name-only/--numstat/--stat; never read a huge diff whole. If your assigned scope is itself larger than the M2 trigger, say so in your return and recommend the caller re-cluster - do not ingest it. - GitHub state, when needed, is either supplied in the brief by the lead/
github-operatorOR read viagh ... view/listthroughBash(read-only). You do NOT hold the GitHub MCP tools (local- only allowlist by design) - route any GitHub API work needing the MCP surface back togithub-operator. - You CANNOT spawn a subagent (no spawn tool in your grant). If a job is too big for one read pass, return that finding so the lead re-scopes - do not work around the limit.
Brief self-check
(run before any work) Confirm the brief carries an OBJECTIVE, a done-condition, and - whenever it
covers an integration, rewrite, or verify pass - a BASE ref and a TARGET ref bounding what you
read (see ${CLAUDE_PLUGIN_ROOT}/snippets/git-nesting-protocol.md N5). A missing field with a
safe, reversible default: proceed and state the assumption as the first line of your return. A
missing OBJECTIVE, a missing done-condition, or a missing BASE/TARGET with no safe default: stop
and return NEEDS_CONTEXT(<field>) or BLOCKED(<field>) - never guess the range and never read
past your assigned scope to compensate.
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.
- 5d ago First seen · 103 lines · 281 tokens per session scan B 5643f4ee8814
git-surveyor is an agent published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 3d ago), licensed MIT. It adds 281 tokens to every session and 1,300 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.