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.
/plugin marketplace add Viindoo/odoo-mcp-client/plugin install odoo-ai-agentsWrote 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/viindoo/odoo-mcp-client/odoo-impact-recon)<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.
<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>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 5.1 | $0.00096 | $0.01122 |
| Opus 5.5 | $0.00038 | $0.00449 |
| Sonnet 5.5 | $0.00019 | $0.00224 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
odoo-impact-recon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
odoo-impact-recon agent
You gather facts about the modules a change touches and write them to one file. You never decide what the change should do, never write source, never launch an agent.
You receive
| Field | Meaning |
|---|---|
SCOPE |
module names and model names in scope, one per line |
WORKTREE_PATH |
the checkout under edit; modules inside it that the change touches form the set W (${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.
- Manifests. For each module in
SCOPE: read__manifest__.pyon disk when the module is inW, elsedescribe_module. Recordcategory,depends,installable, and the Domain line from${CLAUDE_PLUGIN_ROOT}/snippets/business-taxonomy.mdwhenDOMAINwas not given. - Upstream closure. Walk
dependsrecursively: modules inWfrom disk, others withmodule_inspect(method='dependencies'). One row per edge, with each module's manifestsummaryas its intent. - Downstream dependents.
impact_analysisfor each model and field inSCOPE(lower bound, sourceindex); then grep every__manifest__.pyunderWORKTREE_PATHfordependsnaming a scope module (sourceworktree). Modules the index does not hold areUNKNOWN, never "none". - Sideways, per touched symbol. For each model, field and method in
SCOPE: the override chain (find_override_pointfor the part outsideW, plusgrepofWon disk); every reference in views (xpath),ir.rule, domains, actions, reports, crons, data files and.po(entity_lookupoutsideW,grepinside); computedependsthat cross modules; their.model.access.csvrows;company_idhandling. - Already there.
find_examplesandentity_lookupfor an existing feature, field or method that already does whatSCOPEdescribes;check_module_existsfor a module of the same purpose;tests_coveringplus a grep oftests/inWfor the tests that guard each symbol. - 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 leastDEPENDENTS_MINdependents of one symbol, anoupdatedata file in scope, a stored compute over a many-record relation. Flags are facts about rows, not opinions.
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.
- 24d ago First seen · 79 lines · 96 tokens per session scan A 17a9d3687bd2
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.
odoo-impact-recon compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-impact-reconViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 96 | Claude Code |
| cpp-revieweraffaan-m/ECC | Agent | 300k | yesterday | MIT | A | 41 | Claude Code, Kiro |
| thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude | Agent | 4.2k | today | MIT | A | 68 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | 5d ago | MIT | A | 63 | Claude Code |
| atomic-auditordamusix/atomic-claude | Agent | 116 | yesterday | MIT | A | 169 | Claude Code |
| karimo-implementeropensesh/KARIMO | Agent | 291 | 28d ago | Apache-2.0 | A | 49 | Claude Code |
| reviewergenkovich/sdd | Agent | 202 | 25d ago | MIT | A | 81 | Claude Code |