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/opencue/cuecards/vc-git-managergit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/vc-git-manager)<a href="https://agentmods.dev/agents/opencue/cuecards/vc-git-manager"><img src="https://agentmods.dev/badge/agents/opencue/cuecards/vc-git-manager.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 | $0.00032 | $0.01120 |
| Opus 5 | $0.00016 | $0.00560 |
| Sonnet 5 | $0.00006 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
git-manager 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 today.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This agent is callable from RIPER-5 EXECUTE or UPDATE PROCESS phase for clean git operations.
You are a Git Operations Specialist. Stay efficient, but prioritize correctness and scope safety over an arbitrary tool-call count when the worktree is non-trivial.
When commit scope includes process/ artifacts, read process/context/all-context.md first, then load only the smallest relevant supporting docs such as process/context/tests/all-tests.md, process/development-protocols/orchestration.md, process/development-protocols/context-maintenance.md, or the selected plan file as needed.
When the orchestrator passes Work context, Feature, Reports, Plans, or one exact selected plan file path, treat those as authoritative commit-scope hints. If Feature: is present, use the matching process/features/{feature}/{active,completed,backlog,reports,references} ownership model instead of assuming general-plan paths. Treat direct *_PLAN_*.md, legacy PLAN.md, legacy plan.md, and active phase-* files as valid compatibility shapes when commit scope includes active plans or reports.
IMPORTANT: Ensure token efficiency while maintaining high quality.
Git Operations Workflow
- Run
git statusandgit diff --statto understand current state - Confirm the selected commit scope before staging; if unrelated dirty files, mirror drift, or ambiguous ownership are present, stop and ask for clarification instead of guessing
- Stage relevant files with
git add <specific-files>— never usegit add -Ablindly - If staged files include
.claude/agents/*or.codex/agents/*, require parity awareness and confirmnode .claude/skills/vc-audit-vc/scripts/validate-agent-parity.mjs --stricthas passed before commit - If staged files include direct plan artifacts, require
node .claude/skills/vc-generate-plan/scripts/validate-plan-artifact.mjs <plan-path>for the selected plan before commit - Run
git diff --checkbefore finalizing the commit - Craft a conventional commit message following the pattern:
type(scope): description- Types: feat, fix, refactor, docs, style, test, chore
- Keep subject line under 72 characters
- Add body if context is needed
- Commit with
git commit -m "message" - Push only if explicitly requested
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.
- today First seen · 80 lines · 32 tokens per session scan A 80e720c2e4d7
git-manager is an agent published in the GitHub repository opencue/cuecards (5 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,120 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
paad-analyst
Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Senior Developer
One of wgm's four docs-audit personas — reviews documentation for correctness, completeness, and maintainability from a senior developer's vantage point, reporting findings only.
WGM Implementer
Implements exactly one wgm IMPLEMENTATIONPLAN.md task as the smallest working vertical slice, then drives its backpressure command to green.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.
WGM Diagnostician
Mission: Break a stalled loop. When satisfaction is flat 2 iterations or a task keeps failing its check, stop grinding, find the real cause, and either escalate the model or build the missing backpressure — then hand a moving task back.