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/ranvier-technologies/pixir/pixir-delegate-codexnpx skills add Ranvier-Technologies/pixir --skill pixir-delegate-codexgit clone --depth 1 https://github.com/Ranvier-Technologies/pixirWhat 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 | $0.00089 | $0.03053 |
| Opus 5 | $0.00044 | $0.01527 |
| Sonnet 5 | $0.00018 | $0.00611 |
| Haiku 4.5 | $0.00009 | $0.00305 |
Grade A, and why
pixir-delegate-codex 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 2d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pixir Delegate Codex — Pixir workers from a Codex root
You are the Codex CLI/Desktop root orchestrator. Pixir is the worker runtime.
On first use in a session, read the shared practice core at
../pixir-delegate/references/delegation-core.md. Do not re-invent its
routing, refusal, sizing, contracts, closure, or evidence doctrine here; this
file only maps that doctrine onto Codex mechanics.
PREFLIGHT — explicit, no hydration
Codex has no ! command preprocessing. Before any delegation, explicitly choose
and report the Pixir binary you will drive:
- Resolve the binary as an absolute path. Prefer an intentional repo-local
source binary (
./pixirin the target checkout) over a PATH hit; stale PATH binaries are a known failure mode. - Run
<PIXIR_BIN> --versionand<PIXIR_BIN> doctor --json. - In the doctor JSON, find the check with
"id": "source_install_binary"and report its status plus details path; do not treat a PATH version string as proof that the source checkout binary is current. - Classify readiness exactly as the core says:
ready: may delegate.ready_with_warnings: inspect every non-passed check and judge. A missing local source build may be non-blocking for a PATH-driven run; failed auth or unwritable workspace is not.- blocked/error/non-JSON/no binary: do not delegate.
- Record: absolute binary path, version, doctor status, source_install_binary check, and readiness classification for the closure report.
Doctor status and the source_install_binary check are part of the runtime
contract (lib/pixir/doctor.ex; verify current shapes with
pixir doctor --json rather than line numbers).
Codex command posture
There is no Claude-style allowed-tools field here. Codex approval mode and
sandboxing decide whether the root may execute shell commands; Pixir specs decide
what children may do. If the Codex host is read-only, stay with read-only Pixir
workers or ask before changing posture. If approval is required for a command,
obtain it before running the Pixir CLI; do not smuggle side effects through a
child.
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.
- 2d ago First seen · 263 lines · 89 tokens per session scan A 610aa7fad2cd
pixir-delegate-codex is a skill published in the GitHub repository Ranvier-Technologies/pixir (23 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 3,053 once invoked, about $0.0004 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
cross-linker
Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or after any large ingestion to ensure new pages are woven into the…
free-agent-execution
Run an explicitly requested, bounded, non-sensitive coding task through the local free-worker adapter using a verified free OpenCode model. Use only when the user asks to execute a free worker or free agent and accepts the external-model safety boundary.
google-adk-agent-patterns
Define, compose, and wire Google ADK agents with function tools and multi-agent orchestration. Use when writing agent definitions, adding Python function tools, building pipelines with SequentialAgent/LoopAgent/ParallelAgent, or designing router/delegation patterns. Trigger on: adk agent, LlmAgent, SequentialAgent…
corporate-aws-cli
Use when using the AWS CLI against a corporate AWS account after SAML/OIDC federation (e.g. saml2aws, aws sso login), when STS fails with invalid XML or empty responses, when selecting profiles or regions for Terraform or CI/CD stacks, or when validating RDS engine versions with describe-orderable-db-instance-options…
google-adk-setup
Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk…
align
Presents a proposed approach in progressive confirmable chunks with recommended decisions and alternatives. Use when aligning on a design, plan, or technical approach before implementation.