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 skills/viindoo/odoo-mcp-client/git-opsnpx skills add Viindoo/odoo-mcp-client --skill git-opsgit 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/skills/viindoo/odoo-mcp-client/git-ops)<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/git-ops"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/git-ops.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 | $0.00278 | $0.01856 |
| Opus 5 | $0.00139 | $0.00928 |
| Sonnet 5 | $0.00056 | $0.00371 |
| Haiku 4.5 | $0.00028 | $0.00186 |
Grade A, and why
git-ops 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 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.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-ops - the universal git/github front door
Any git or GitHub need routes through here. The contract: git churn happens in a delegated or
inline-bounded context so the CALLER'S context stays clean, code is NEVER lost, and the work scales
from a few lines to thousands of files. GitHub work prefers the GitHub MCP, falling back to gh.
Your job is to ROUTE and DISPATCH, not to execute. You are a dispatcher: you classify the op, pick the mode, and hand the actual work to the specialist agent that owns the safety contract for it. Do NOT run rebases, merges, cherry-picks, resets, pushes, PR creates/merges, or read a full diff/PR body yourself in this context - a worker does that in its own context and returns a compact result. The ONE exception is a genuinely bounded, low-risk read on the INLINE allowlist below; when in doubt whether an op qualifies, it does not - delegate it. This is what keeps the caller's context clean and every mutation behind its backup/verify/confirm gate.
Step 1 - classify the op
Bucket the request into one of: READ (status/log/diff/blame/bisect-read), REVERSIBLE-WRITE
(stage/commit/clone/init/stash, fetch/pull-rebase/merge/cherry-pick/branch/tag/worktree/non-force
push/forward-port/backport/bisect-run), DESTRUCTIVE-REWRITE
(rebase -i/squash/split/amend/reset/filter-repo/force-with-lease), or GITHUB
(PR/issue/review/release/CI/fork). bisect-read (a completed session's git bisect log/view, no
checkout) is a bounded READ; bisect-run (a LIVE git bisect start/good/bad/run session,
which repeatedly checks out commits) is checkout-mutating and MUST classify as REVERSIBLE-WRITE,
never READ.
Step 2 - route by the delegation decision
Apply ${CLAUDE_PLUGIN_ROOT}/snippets/git-delegation-decision.md. Pick ONE of three modes by
OUTPUT SIZE and RISK (never step count):
- INLINE - bounded-output, low-risk single op (
git status,git log -n,git show --stat, ref/branch existence,git diff --stat/--name-only): run the safe command directly. NEVER inline unbounded output (full PR body, file contents, a full diff) - "read one PR" is DELEGATE. - SINGLE-DELEGATE - one medium op (rebase, cherry-pick range, analyze one diff, PR
review/create, issue triage): cold-spawn ONE leaf - READ cognition ->
git-surveyor(read-only); local mutation (reversible OR destructive) ->git-operator(carries the safety contract); GitHub API ->github-operator(MCP-first / gh-fallback). Resolve the model tier from${CLAUDE_PLUGIN_ROOT}/snippets/git-model-tiers.md(single-delegate op-class table, first-match-wins); pass it as the launch'smodelparam AND putDISPATCH MODEL: <tier>as the first line of the brief. - PHASED-PIPELINE - large/complex (>500 files OR >10k LOC OR multi-commit rewrite OR
thousand-file backport, per
${CLAUDE_PLUGIN_ROOT}/snippets/git-scale-protocol.mdM2): cold-spawngit-pipeline-lead(opus). It runs P1 map -> P2 evaluate -> P3 strategy + HUMAN-CONFIRM -> P4 execute -> P5 verify below the caller, and returns only the final result. P3 strategy and the human-confirm gate are the LEAD's job, not the surveyor's.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 120 lines · 278 tokens per session scan A 697a4d48dbe0
git-ops is a skill published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 2d ago), licensed MIT. It adds 278 tokens to every session and 1,856 once invoked, about $0.0014 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…