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 agentmods add skills/microsoft/vscode/update-codex-sdknpx skills add microsoft/vscode --skill update-codex-sdkgit clone --depth 1 https://github.com/microsoft/vscodeWhat 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 | $0.00070 | $0.01033 |
| Opus 5 | $0.00035 | $0.00517 |
| Sonnet 5 | $0.00014 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
update-codex-sdk 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 today.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update the bundled Codex SDK
The public npm latest version is not necessarily installable in VS Code CI. The Azure pipeline uses the private vscode feed, where CFS normally quarantines new third-party package versions for seven days. Select a version from that feed before changing files.
Select a CI-available version
Run the helper from the repository root:
node --experimental-strip-types .agents/skills/update-codex-sdk/scripts/latest-private-version.ts
It obtains an Azure DevOps access token from the signed-in Azure CLI, queries the same feed used by build/azure-pipelines/dependencies-check.yml, and reports the newest stable release for which the root package and every platform binary alias declared by that release are present. It never prints the token. If Azure CLI authentication is missing or expired, ask the user to authenticate rather than falling back to the public registry.
To check a user-requested version explicitly:
node --experimental-strip-types .agents/skills/update-codex-sdk/scripts/latest-private-version.ts --version 0.149.1
Use --raw when only the latest complete version string is needed. Do not change the repository or global npm registry merely to probe availability.
Update every pin
Set CODEX_VERSION to the selected exact version. Keep committed lockfile URLs on https://registry.npmjs.org/; the private feed determines CI eligibility but is not written into source lockfiles.
CODEX_VERSION=0.149.1
npm install --save-dev --save-exact --ignore-scripts --registry=https://registry.npmjs.org "@openai/codex@$CODEX_VERSION"
npm --prefix build/agent-sdk/agents/codex install --save-exact --package-lock-only --ignore-scripts --registry=https://registry.npmjs.org "@openai/codex@$CODEX_VERSION"
Use apply_patch to set build/codex/codex-version.txt to the same version, then regenerate the vendored app-server client:
npm run codex:gen-protocol
The expected version-bearing files are:
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.
- today First seen · 89 lines · 70 tokens per session scan A 95f94eb4db74
update-codex-sdk is a skill published in the GitHub repository microsoft/vscode (190,384 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 1,033 once invoked, about $0.0003 per session on Opus 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 2026-09-02.
Other skills, from other repositories
analyze-sessions
Analyzes your local Copilot CLI sessions for dotnet/maui to drive iterative improvements to the PR-review agent (and other agents, skills, and instruction files). Runs a select → extract → score → judge → cluster → propose → emit-eval loop: a deterministic core ranks your worst / most-expensive sessions, then the…
learn-from-pr
Analyzes a completed PR to extract lessons learned from agent behavior. Use after any PR with agent involvement - whether the agent failed, succeeded slowly, or succeeded quickly. Identifies patterns to reinforce or fix, and generates actionable recommendations for instruction files, skills, and documentation.
otel-queries
Guidance for querying and interpreting Copilot and agentic workflow OpenTelemetry token and execution metrics.
composio
Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help…
deepseek-harness-eac-dev
面向 Deepseek Harness EAC 源码仓库的全栈开发与维护技能。处理 Tauri/Rust 桌面壳、Node sidecar、Web bridge、DSH 插件与 preset、profile 治理、更新打包、可靠性修复、测试验收和发布准备时使用；不用于客户端功能使用说明，也不负责专项 JS 到 TS 迁移。.
sensei
WORKFLOW SKILL — Evaluates and improves agent skill quality in .github/skills/ using waza. Scores skill compliance (frontmatter, triggers, anti-triggers, eval coverage), suggests improvements, runs eval suites, and iterates until target quality is reached. INVOKES: waza CLI, askuser. USE FOR: evaluate skill, improve…