Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentprism/agentprism-workflows --skill codex-update-compatgit clone --depth 1 https://github.com/agentprism/agentprism-workflowsWrote 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/skills/agentprism/agentprism-workflows/codex-update-compat)<a href="https://agentmods.dev/skills/agentprism/agentprism-workflows/codex-update-compat"><img src="https://agentmods.dev/badge/skills/agentprism/agentprism-workflows/codex-update-compat/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/skills/agentprism/agentprism-workflows/codex-update-compat"><img src="https://agentmods.dev/badge/skills/agentprism/agentprism-workflows/codex-update-compat.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 | $0.00086 | $0.00556 |
| Opus 5.5 | $0.00034 | $0.00222 |
| Sonnet 5.5 | $0.00017 | $0.00111 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
codex-update-compat 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Update Compat
Use this workflow to safely upgrade Codex and close update-induced regressions.
Workflow
- Inspect update scope before changing code. Run:
git log --oneline -n 5
git show --name-only --oneline -n 1
Focus first on package.json, package-lock.json, and generated src/app-server/** changes.
- Run typecheck and tests immediately. Run:
npm run typecheck
npm test
Treat type errors as the migration guide for required protocol changes.
- Fix runtime compatibility in source files. Typical hotspots:
src/CodexAcpClient.ts: thread start/resume params and initialize capabilitiessrc/AgentMode.ts: sandbox policy shape changessrc/CodexEventHandler.ts: new/changed server notificationssrc/CodexAcpServer.ts: history replay for newThreadItemvariantssrc/CodexToolCallMapper.ts: mapping new tool-like items to ACP events
-
Fix test fixtures and snapshots. Update typed fixtures for new required fields instead of weakening types. Then update snapshots only after behavior is intentionally verified.
-
Re-run targeted suites, then full checks. Run focused tests for touched behavior, then:
npm run typecheck
npm test
Non-Trivial Changes: Ask Before Finalizing
When migration requires behavior decisions (not only schema fixes), ask the user first. Examples:
- Enabling/disabling experimental flags (
persistExtendedHistory,experimentalApi) - User-visible messaging changes for new events (e.g., model reroute wording)
- Converting integration tests to mocks or skipping env-dependent tests
Event Mapping Rule
Do not silently drop new event/item variants if they should be visible to users. Map them to ACP updates:
- Tool-like operations ->
tool_call/tool_call_update - Informational reasoning/infra events ->
agent_thought_chunk(if user-meaningful) - Internal/noise events -> explicit no-op case (documented in switch)
References
For common break patterns and ready fixes, read:
references/codex-update-playbook.md
What ships with it
2 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.
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.
- 1mo ago First seen · 66 lines · 86 tokens per session scan A 96fec49880bc
codex-update-compat is a skill published in the GitHub repository agentprism/agentprism-workflows (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 86 tokens to every session and 556 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
configure-coddy
Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands for config.yaml and commits only after the user confirms saving; MCP servers are entries of the mcp.json files. Load…
crossreview
Run when the user invokes /crossreview (or /crossreview:setup to choose the reviewers) or asks for a cross-review, a quorum review or a second opinion from other agents or models: fan a code review (uncommitted work, a branch, a commit range, files, a plan or a document) out to several console code agents (Claude…
rpa-init
Run when the user invokes /rpa-init or asks to onboard or warm up context on a repository. The agent studies code, reads documentation and test code, sets up the dev environment as the project expects, runs tests, and writes a short project report. No extra user brief is required.
rpa-gen-rules
Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.
rpa-feat
Run when the user invokes /rpa-feat together with a clear feature description (for example issue text). BDD workflow: plan, failing tests, implementation, green tests, full suite, docs and examples, linter at the end. Will not work correctly without the user supplying what to build.
rpa-bugfix
Run when the user invokes /rpa-bugfix together with a clear bug description (expected vs actual, reproduction). Reproduction test first, then fix, full test suite, short report. Will not work correctly without the bug details.