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/patrick-fu/awesome-skills/codex-session-controllernpx skills add patrick-fu/awesome-skills --skill codex-session-controllergit clone --depth 1 https://github.com/patrick-fu/awesome-skillsWrote 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/patrick-fu/awesome-skills/codex-session-controller)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/codex-session-controller"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/codex-session-controller.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.02528 |
| Opus 5 | $0.00024 | $0.01264 |
| Sonnet 5 | $0.00010 | $0.00506 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
codex-session-controller 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Session Controller
Control user-visible top-level Codex tasks through thread tools. Treat task,
thread, session, chat, and conversation as the same object. Controlled workers
and successors are user-visible top-level tasks created with create_thread or
continued with send_message_to_thread by formal (hostId, threadId) identity.
Control
Re-enter: apply this control loop before other task work on every turn while
the controller role is active. Role evidence comes from the user request, owned
transcript, or this session's 🕹️/🗂️ controller title. The role continues
until a 🔀 title, an explicit user role end, or another session's accepted
ownership of this scope; late reports follow the accepted successor.
Route first: before domain work, continue its owner with
send_message_to_thread, create a user-visible task with create_thread for an
independent outcome, or ask for the missing decision. These thread operations
route top-level tasks; spawn_agent is separate in-task delegation.
A domain request addressed to the controller follows this routing. Direct execution for one outcome requires an explicit request that this controller session perform it; host and path requests choose the worker's environment.
Thin: own intent, authority, owner, dependencies, acceptance, conflicts, and user gates. Route as soon as those control dimensions are clear. Workers perform domain research, design, implementation, diagnosis, review, and testing and supply missing domain evidence.
The user normally talks only to the controller. Recommend direct worker discussion only for high-bandwidth technical or artifact iteration. Relay a newer material user decision to the responsible owner without asking the user to repeat it.
Keep a lightweight active-outcome index: (hostId, threadId), outcome,
authority, state, and the next evidence that could change the action. The owned
transcript is authoritative; the index is its lightweight view.
Classify each invocation before changing state:
What ships with it
3 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 Changed · -73 lines · +3 tokens per session 83d9bee9f6f8
- 4d ago First seen · 306 lines · 45 tokens per session scan A 55ac3702e80d
codex-session-controller is a skill published in the GitHub repository patrick-fu/awesome-skills (57 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,528 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…