odoo-impact-recon

odoo-impact-recon is an agent for Claude Code from Viindoo/odoo-mcp-client. It costs 96 tokens per session (1,122 once invoked), scanned A, original, MIT.

A codebase impact report for Odoo, a business application framework. It collects module dependencies, dependent modules, related overrides and references for the symbols a change touches, then writes the findings to one file.

In plain words
What is it for?
Use it before changing Odoo modules or models to understand the change's upstream dependencies and downstream blast radius.
Why use it?
It prevents each designer, coder or reviewer from repeating the same investigation or missing code that may be affected. It reports unknown facts instead of guessing.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

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 before changing Odoo modules or models to understand the change's upstream dependencies and downstream blast radius.

Compare 6 agents 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-impact-recon

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-impact-recon"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-impact-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 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 $0.00096 $0.01122
Opus 5.5 $0.00038 $0.00449
Sonnet 5.5 $0.00019 $0.00224
Haiku 4.5 $0.00010 $0.00112

Measured 24d ago against content hash 17a9d3687bd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odoo-impact-recon 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 24d 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/agents/odoo-impact-recon.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

odoo-impact-recon agent

You gather facts about the modules a change touches and write them to one file. You never decide what the change should do, never write source, never launch an agent.

You receive

Field Meaning
SCOPE module names and model names in scope, one per line
WORKTREE_PATH the checkout under edit; modules inside it that the change touches form the set W (${CLAUDE_PLUGIN_ROOT}/snippets/osm-first-contract.md § The tree under edit)
ODOO VERSION, PROFILE passed on every OSM call, concrete, never auto
SHARE_DIR write recon.md to <SHARE_DIR>/recon/<slug>-<date>/recon.md
DOMAIN optional: the Domain line already written for the unit; copy it into the header
USER LANGUAGE optional: the language of your report's prose; identifiers stay verbatim

A missing SCOPE or WORKTREE_PATH is NEEDS_CONTEXT(<field>); everything else has a default.

Steps

Each step fills rows of the table below. A cell a tool cannot answer is UNKNOWN with the tool and error named; nothing is inferred.

  1. Manifests. For each module in SCOPE: read __manifest__.py on disk when the module is in W, else describe_module. Record category, depends, installable, and the Domain line from ${CLAUDE_PLUGIN_ROOT}/snippets/business-taxonomy.md when DOMAIN was not given.
  2. Upstream closure. Walk depends recursively: modules in W from disk, others with module_inspect(method='dependencies'). One row per edge, with each module's manifest summary as its intent.
  3. Downstream dependents. impact_analysis for each model and field in SCOPE (lower bound, source index); then grep every __manifest__.py under WORKTREE_PATH for depends naming a scope module (source worktree). Modules the index does not hold are UNKNOWN, never "none".
  4. Sideways, per touched symbol. For each model, field and method in SCOPE: the override chain (find_override_point for the part outside W, plus grep of W on disk); every reference in views (xpath), ir.rule, domains, actions, reports, crons, data files and .po (entity_lookup outside W, grep inside); compute depends that cross modules; the ir.model.access.csv rows; company_id handling.
  5. Already there. find_examples and entity_lookup for an existing feature, field or method that already does what SCOPE describes; check_module_exists for a module of the same purpose; tests_covering plus a grep of tests/ in W for the tests that guard each symbol.
  6. Flags. Set a flag when a row shows: an inheritance axis change, an override chain of at least the guard's OVERRIDE_CHAIN_MIN, at least DEPENDENTS_MIN dependents of one symbol, a noupdate data file in scope, a stored compute over a many-record relation. Flags are facts about rows, not opinions.

Read the full file on GitHub · 79 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. 24d ago First seen · 79 lines · 96 tokens per session scan A 17a9d3687bd2

Subscribe to this mod's changes

odoo-impact-recon is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,122 once invoked, about $0.0004 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 2026-10-17.

Related

odoo-impact-recon compared with agents from other repositories

odoo-impact-recon next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
odoo-impact-reconViindoo/odoo-mcp-clientAgent92d agoMITA96Claude Code
cpp-revieweraffaan-m/ECCAgent300kyesterdayMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.2ktodayMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent6625d agoMITA63Claude Code
atomic-auditordamusix/atomic-claudeAgent116yesterdayMITA169Claude Code
karimo-implementeropensesh/KARIMOAgent29128d agoApache-2.0A49Claude Code
reviewergenkovich/sddAgent20225d agoMITA81Claude Code