odoo-pr-monitoring

odoo-pr-monitoring is a skill for Claude Code from Viindoo/odoo-mcp-client. It costs 267 tokens per session (4,899 once invoked), scanned C, original, MIT.

A post-pull-request monitor for an Odoo development run. A pull request is a proposed code change awaiting automated checks and human review; this tool watches those checks and review status without merging the change.

In plain words
What is it for?
Use it to poll an Odoo pull request, detect failed checks or review issues, and continue the fix-and-review workflow.
Why use it?
It keeps CI failures, warnings, and review feedback visible after the pull request is opened and routes problems for investigation.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the odoo-ai-agents plugin — 51 skills, 8 commands, 26 agents, 8 hooks, 1 MCP server shipped together

Good fit Use it to poll an Odoo pull request, detect failed checks or review issues, and continue the fix-and-review workflow.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Viindoo/odoo-mcp-client
Claude Code
/plugin install odoo-ai-agents

Made for: Claude Code.

Or install odoo-ai-agents, the plugin that ships this one along with the rest of its 51 skills, 8 commands, 26 agents, 8 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 odoo-pr-monitoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-pr-monitoring/github.svg)](https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-pr-monitoring)
Your own site
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-pr-monitoring"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-pr-monitoring/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.

agentmods 80×15 button for odoo-pr-monitoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-pr-monitoring"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-pr-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 267 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00267 $0.04899
Opus 5 $0.00133 $0.02449
Sonnet 5 $0.00053 $0.00980
Haiku 4.5 $0.00027 $0.00490

Measured 9d ago against content hash 4e2be782a01f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

odoo-pr-monitoring scanned grade C 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`find <ISOLATE_DIR>/pr-monitoring/ -maxdepth 1 -type f -name '*.md' -mmin +43200 -exec rm -rf {} +`
plugins/odoo-ai-agents/skills/odoo-pr-monitoring/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

odoo-pr-monitoring - the post-PR lifecycle owner (poller)

Where this sits in the flow

Begins where run-harness's terminal integrate land-tail stops at "PR opened": once every node in that repo is terminal and a DONE verification node covers every module its coding nodes touched, run-harness squashes the repo's run-integration branch, fresh FIRST-pushes it (non-force), opens ONE PR for that repo (run-integration -> principal), and STOPS (never merges). The surviving invariant is exactly ONE PR per repo per run. monitor and merge are ORDINARY plan nodes that run-harness's pick_ready dispatches like any other node - monitor depends_on integrate, merge depends_on monitor - and this skill is what runs each time either is dispatched; run-harness never materializes a second one dynamically. CI runs minutes-to-hours and review takes hours-to-days, so a dispatch of monitor never holds the run's turn open for that long: each poll tick reads once, classifies, and PARKS - it emits a NEEDS_NEXT Continuation Contract naming itself in next[] so the driver's turn ends cleanly, and a later /loop tick or /schedule cron re-invocation re-attaches via run-<id>.json and resumes. Once the watch classifies green + approved + mergeable, the monitor node itself reaches DONE - it does NOT also perform the merge; that is the separate merge node's job, dispatched only once monitor is DONE, so the outward L2 gate keeps its own depends_on edge and its own gate_log entry.

run-harness's last verification node for this repo closes green  ->  integrate land-tail: squash + fresh first-push + open ONE PR  ->  STOP at "PR opened"
   --- `monitor` node (run-harness dispatches it like any other node; each tick PARKS via NEEDS_NEXT instead of blocking the turn) ---
odoo-pr-monitoring  (poll via /loop in-session | /schedule cron)
   -> any CI warning/error/fail  ->  odoo-debug (D3: root-cause)  ->  odoo-coding (fix)
        -> proposed re-push is HUMAN-GATED (X2); max_review_rounds cap; exhaustion -> BLOCKED
   -> green + approved + mergeable  ->  `monitor` node reaches DONE
   --- `merge` node (depends_on: monitor; run-harness dispatches it once monitor is DONE) ---
odoo-pr-monitoring  ->  present merge approval gate  ->  merge (git-ops)
        -> post-merge cleanup (worktrees/branches/tag via git-ops)

Read the full file on GitHub · 266 lines

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. 9d ago First seen · 266 lines · 267 tokens per session scan C 4e2be782a01f

Subscribe to this mod's changes

odoo-pr-monitoring is a skill published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed 6d ago), licensed MIT. It adds 267 tokens to every session and 4,899 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.