odoo-planning

odoo-planning is a skill for Claude Code from Viindoo/odoo-mcp-client. It costs 21 tokens per session (3,978 once invoked), scanned A, original, MIT.

A planning coordinator that turns an approved Odoo technical design into an execution plan for code and documentation. It assigns the work to separate planners and defines dependency order and delivery sequence.

In plain words
What is it for?
Use it to prepare a gateable delivery plan before implementation, including code tasks, documentation tasks, and their dependencies.
Why use it?
It provides a single plan for deciding what must be built first and when supporting documentation should be produced.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; names the ExitPlanMode tool.

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 — 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers shipped together

Good fit Use it to prepare a gateable delivery plan before implementation, including code tasks, documentation tasks, and their dependencies.

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 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers.

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-planning

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-planning"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,978 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00021 $0.03978
Opus 5.5 $0.00008 $0.01591
Sonnet 5.5 $0.00004 $0.00796
Haiku 4.5 $0.00002 $0.00398

Measured 7d ago against content hash 9633f18ccdd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odoo-planning 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 7d 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.

plugins/odoo-ai-agents/skills/odoo-planning/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Odoo Planning - the execution plan between design and code

Planning step only. Output: <SHARE_DIR>/plans/<slug>-<date>.md (resolve <SHARE_DIR>/<ISOLATE_DIR> via the resolve-capture-substitute protocol in ${CLAUDE_PLUGIN_ROOT}/snippets/state-root-resolution.md before the first Read/Write/Edit of a state-root path in this skill) - never production source. You do NOT compute the plan and do NOT write code: launch odoo-planner, then own the plan gate and the hand-off.

gap/brl  ->  odoo-solution-design (TDD + index.yaml)  ->  HUMAN approves SRS and design (text)
   ->  odoo-planning -> odoo-planner (the plan: build nodes + the lifecycle tail)
   ->  EnterPlanMode -> the ONE plan gate -> ExitPlanMode
   ->  intake Phase P serializes run-<id>.json  ->  the main agent runs the plan

Role

Turn an approved technical design into ONE lifecycle plan (the build nodes and the lifecycle tail, documentation included) by launching ONE leaf planner, odoo-planner. The plan is run by the main agent per ${CLAUDE_PLUGIN_ROOT}/skills/odoo-intake/references/plan-mode-schema.md § Running the plan. The documentation of the change is the tail nodes docs-module then docs-site (plan-mode-schema.md § Default tail), run after code/review/QA when their when: holds, ungated. The documentation target (module, site, both, none) comes from odoo-intake in the brief.

Input port - read the upstream artifacts BY POINTER (before dispatch)

Locate the upstream artifacts and pass their paths to the planner (never paste or re-derive them):

  • Design DAG (OPTIONAL - none when no design was authored) - <SHARE_DIR>/designs/<master-slug>/index.yaml (dag_layers + dependency direction) for a master-child design, or the single-mode <SHARE_DIR>/designs/<slug>-<date>.md. When one exists the planner CONSUMES it and never recomputes it. When none exists the plan is derived from the development work and the field is an explicit none.
  • Gap matrix - <SHARE_DIR>/gap-analysis/<slug>-<date>/gap-matrix.jsonl (or a BRL RTM under <SHARE_DIR>/brl/<job-id>/): per-requirement effort tier, drives effort.
  • QA oracle (OPTIONAL - usually ABSENT at planning time) - <ISOLATE_DIR>/qa/<slug>-scenarios.md. The acceptance node is ALWAYS authored statically, never omitted for lack of an oracle. When the oracle is absent, the plan sources the node's criteria from the design's §9 Acceptance Criteria; when present, the plan wires its review/acceptance stages to it.
  • Survey (OPTIONAL - ALWAYS an explicit value) - <SHARE_DIR>/survey/<slug>-<date>/synthesis.md, forwarded in this skill's brief INPUTS when intake's hand-off carried a deep-survey synthesis. State none explicitly to odoo-planner when absent, and thread it onward the same way (§ P1).

Read the full file on GitHub · 240 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. 7d ago Changed · -2 lines 9633f18ccdd4
  2. 16d ago Changed · +10 lines 503d14006dc4
  3. 17d ago Changed · -2 tokens per session ce8b54159217
  4. 20d ago Changed · -109 lines 2afd169494db
  5. 24d ago Changed · -65 lines dc6d4bb40feb
  6. 29d ago Changed · +12 lines 0e2b4a09b3da
  7. 1mo ago Changed · -10 lines · -187 tokens per session 80f9eb635dc0
  8. 1mo ago Changed a58a2983f1d7
  9. 1mo ago Changed a9133eed7140
  10. 1mo ago First seen · 404 lines · 210 tokens per session scan A 77b5d9edb37d

Subscribe to this mod's changes

odoo-planning is a skill published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 3,978 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

odoo-planning compared with skills from other repositories

odoo-planning next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
odoo-planningViindoo/odoo-mcp-clientSkill92d agoMITA21Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k3d agoMITA200Claude Code, Codex
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill315k6d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code