guard-git-watch

guard-git-watch is an agent for coding agents from giggsoinc/raven. It costs 57 tokens per session (289 once invoked), scanned A, original, MIT.

A protection agent that watches access to sensitive files such as environment files, SSH keys, and configuration manifests. It blocks unapproved reads or changes and records an alert.

In plain words
What is it for?
It is for guarding credentials, private keys, Raven configuration files, and the list of approved skills while coding tools run.
Why use it?
It reduces the risk of an add-on exposing secrets or changing important project settings without permission.

Agent

Part of the raven plugin — 28 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add agents/giggsoinc/raven/guard-git-watch
Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Or install raven, the plugin that ships this one along with the rest of its 28 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server.

Wrote 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.

agentmods badge for guard-git-watch

README.md
[![agentmods](https://agentmods.dev/badge/agents/giggsoinc/raven/guard-git-watch.svg)](https://agentmods.dev/agents/giggsoinc/raven/guard-git-watch)
Your own site
<a href="https://agentmods.dev/agents/giggsoinc/raven/guard-git-watch"><img src="https://agentmods.dev/badge/agents/giggsoinc/raven/guard-git-watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 289 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.00289
Opus 5 $0.00028 $0.00144
Sonnet 5 $0.00011 $0.00058
Haiku 4.5 $0.00006 $0.00029

Measured 3d ago against content hash ba4c437ab4c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guard-git-watch 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 3d 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.

agents/guard-git-watch.md · 32 lines

What it actually says

Skill Guard — Sensitive File Protection

Monitored files (NEVER read by any skill)

  • .raven/manifest.secrets.json
  • .env, .env.*
  • *.pem, *.key, id_rsa, id_ed25519
  • .claude/settings.json (read-only — no skill may modify)
  • .raven/manifest.json (read-only for skills — modify via /raven-approve only)

On detection

If any skill attempts to read or modify monitored files:

  1. HARD BLOCK the action immediately
  2. Output: "⚠️ Skill {name} attempted restricted file access — blocked"
  3. Log: skill name, file attempted, timestamp
  4. Warn developer to audit the skill

Approved skills check

On session start, compare loaded skills against manifest.approved_skills. Any unlisted skill → WARN: "Unapproved skill detected: {name}. Add to manifest.approved_skills to permit."

Changes

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.

  1. 3d ago First seen · 32 lines · 57 tokens per session scan A ba4c437ab4c9

Subscribe to this mod's changes

guard-git-watch is an agent published in the GitHub repository giggsoinc/raven (5 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 289 once invoked, about $0.0003 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 2026-08-31.