odoo-forward-port

odoo-forward-port is a skill for Claude Code from Viindoo/odoo-mcp-client. It costs 24 tokens per session (4,167 once invoked), scanned C, original, MIT.

A workflow for moving fixes and features from an older Odoo major version to a newer one. A forward-port reapplies the intended behavior to the newer codebase, rather than simply copying old code.

In plain words
What is it for?
Use it to forward-port commits, adapt code and tests, and verify that the intended behavior survives on the target Odoo version.
Why use it?
It helps identify changes that are already present, no longer fit, or need adaptation, even when Git reports a clean merge.

Skill for Claude Code

Written for Claude Code: argument-hint 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 — 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers shipped together

Good fit Use it to forward-port commits, adapt code and tests, and verify that the intended behavior survives on the target Odoo version.

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-forward-port

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-forward-port"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-forward-port.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,167 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 $0.00024 $0.04167
Opus 5.5 $0.00010 $0.01667
Sonnet 5.5 $0.00005 $0.00833
Haiku 4.5 $0.00002 $0.00417

Measured 7d ago against content hash d61dd68da3df, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

odoo-forward-port 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 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.

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>/forward-port/ -mindepth 1 -maxdepth 1 -type d -mmin +43200 -exec rm -rf {} +`
plugins/odoo-ai-agents/skills/odoo-forward-port/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Forward-port conductor: own the git topology, the per-commit SEMANTIC pipeline and the subagent lifecycle. The git unit is the RANGE (Hard rule 2). Delegate leaf work and every P6 / P6-TEST / P7 gate to specialist agents and read-only delegates ([[fp-symbol-survival-check]] - Who runs this check); you record verdicts and finding lines, never produce them. A green merge + lint + install proves nothing (Hard rules 4-5). Code, module docs and docs-site pages all run HERE; P0 picks the lane (docs-site: references/fp-docs-site-lane.md, replacing only the content phases).

Route out: no commit -> odoo-coding; API delta only -> odoo-version-diff; review -> odoo-code-review; deprecation sweep -> odoo-deprecation-audit; same-series replay -> odoo-git-rebase; whole-cluster upgrade -> odoo-modules-upgrade; standalone design -> odoo-solution-design; N disjoint WIs with cherry-pick + squash -> odoo-planning; upgrade plan only -> /odoo-plan-upgrade.

/odoo-forward-port <source-ref> <target-branch> [--scope <mod1,mod2>] [--since <sha>], parsed from $ARGUMENTS in P0 (missing source-ref / target-branch -> ask once before any read or git-ops request). ONE shape, no mode flag; to land PART of a branch pass that sub-range's TIP SHA.

Hard rules

  1. Target-branch-lock - NEVER checkout, switch, commit, merge, rebase, reset or push target branch B (reads allowed). Integrate only in the JOB-tier worktree fp/<slug> branched FROM B (<path>/fp-integration); P8 adapts DIRECTLY there, no per-module child worktree. Every mutation goes via git-toolkit:git-ops (${CLAUDE_PLUGIN_ROOT}/snippets/git-delegation.md); saga: ${CLAUDE_PLUGIN_ROOT}/skills/_shared/integration-loop.md.
  2. ONE merge, ONE merge commit - a single true merge of the range TIP, left uncommitted ([[fp-merge-absorption]]), closed by one merge commit; every source SHA is preserved; the commit count never sets the merge count. BANNED: (i) merging or committing one source commit at a time; (ii) cherry-pick at ANY granularity. A batch merges its own tip once; a FROZEN source merges alike.
  3. Intent before code - forward the behavior, never a source hunk. SSOT [[fp-intent-4outcome]].
  4. Verify by behavior - the forwarded INTENT test passes on the target AND its node's test leg broke the rule and restored the code (${CLAUDE_PLUGIN_ROOT}/snippets/test-sensitivity-contract.md); a bucket-(a) source test passes with the commit's code out of play.
  5. Symbol-survival before adapt - after every merge run P6 on conflicted AND merge-clean-but- source-touched files; resolve every broken symbol into a bucket first.
  6. Human gates are P4 (plan) and P12 (PR merge); local merges are self-decided. P4 is the one Plan-Mode gate (${CLAUDE_PLUGIN_ROOT}/snippets/planning-gate-contract.md § One Plan-Mode gate); P10 concludes each batch on fp/<slug> unasked and lands nothing on B; no auto-merge.
  7. Buckets (a)/(d) are still ABSORBED - never narrow the range to exclude them; record bucket + reason on the merge-log.md row and in the merge commit body.
  8. Verify subagent claims - never trust a leaf's GREEN; run the P9 verify yourself per batch.
  9. Acceptance (P11) is mandatory, narrow escape only: no DONE without ACCEPTED or a recorded escape.
  10. i18n reconcile is mandatory, narrow escape only: 8e COMPUTES the conditions, P9.5 DISPATCHES odoo-i18n per batch; skip only via an enumerated escape on the module's merge-log.md row (${CLAUDE_PLUGIN_ROOT}/snippets/i18n-mandate-contract.md); no DONE without a result or escape for each i18n_due: yes module.
  11. Descriptor filename resolves ONCE, per side - from ${CLAUDE_PLUGIN_ROOT}/snippets/odoo-era-boundaries.md row 6: at P0 record <tgt-descriptor> (target_ref) and <src-descriptor> (source_ref; they can differ). Reuse those literals for every descriptor read, path and assertion: installable, depends, version, manifest_path, history_dump_path, and the P9 addons-coverage assertion. An absent descriptor may mean the WRONG FILENAME was opened; a failed read never justifies dropping the module or guessing installable / depends / demo.

Read the full file on GitHub · 158 lines

Files

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.

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 · -241 lines d61dd68da3df
  2. 8d ago Changed b3749e10d313
  3. 17d ago Changed · -323 lines · +5 tokens per session da1f1751f89a
  4. 19d ago Changed · -1 lines e88b177cae63
  5. 20d ago Changed · -250 lines a591a5370f83
  6. 21d ago Changed · +4 lines a3d58235751a
  7. 24d ago Changed · -4 lines 58542e6ab98f
  8. 29d ago Changed · -2 lines 10d6c5a17b34
  9. 1mo ago Changed af02c6ef4225
  10. 1mo ago First seen · 975 lines · 19 tokens per session scan C 9302e6f1071c

Subscribe to this mod's changes

odoo-forward-port is a skill published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 4,167 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

odoo-forward-port compared with skills from other repositories

odoo-forward-port next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
odoo-forward-portViindoo/odoo-mcp-clientSkill92d agoMITC24Claude Code
merge-batchdiegosouzapw/OmniRouteSkill85k2d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15ktodayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6ktodayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4kyesterdayMITA51Claude Code, Codex