Borrowing it
Nothing to install: this file belongs to Ranvier-Technologies/pixir. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Ranvier-Technologies/pixir/main/.agents/skills/pixir-delegate/SKILL.mdgit clone --depth 1 https://github.com/Ranvier-Technologies/pixirWrote 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/ranvier-technologies/pixir/pixir-delegate)<a href="https://agentmods.dev/skills/ranvier-technologies/pixir/pixir-delegate"><img src="https://agentmods.dev/badge/skills/ranvier-technologies/pixir/pixir-delegate/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/ranvier-technologies/pixir/pixir-delegate"><img src="https://agentmods.dev/badge/skills/ranvier-technologies/pixir/pixir-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.04827 |
| Opus 5.5 | $0.00050 | $0.01931 |
| Sonnet 5.5 | $0.00025 | $0.00965 |
| Haiku 4.5 | $0.00013 | $0.00483 |
Grade A, and why
pixir-delegate 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pixir Delegate — subagents without a wrapper agent
Runtime state, hydrated by the harness at invocation. Preprocessing is this
variant's contract: if the line below reads as a raw placeholder, you are on
the wrong variant; use pixir-delegate-codex (explicit preflight, no
hydration) instead of working around it here.
Caller workspace: !pwd
Binary preflight — preserve the caller workspace
Resolve once before running version, doctor, rehearsal, or a real delegation.
scripts/resolve-binary.sh, scripts/fanout.sh, and scripts/steer.sh share
this deterministic rule:
- A nonempty
PIXIR_BINis an explicit override and wins. Validate that it names an executable file and resolve it to an absolute path. Relative paths are relative to the caller workspace; a bare command name is looked up on PATH. An invalid override is an error, never permission to fall back. - Otherwise prefer
./pixirin the caller workspace, not in the skill checkout. If that candidate exists but is not an executable file (including a directory or dangling symlink), stop with an error instead of using PATH. - Only when no local candidate exists, resolve
pixirfrom PATH to an absolute executable path. An emptyPIXIR_BINbehaves like an unset one.
Discover this loaded skill's directory and set PIXIR_DELEGATE_SKILL_DIR to
its absolute path; do not change CWD to find or invoke it. Run the shared
preflight in Bash from the target workspace (obtain host approval if required):
source "$PIXIR_DELEGATE_SKILL_DIR/scripts/resolve-binary.sh"
PIXIR_BIN="$(pixir_resolve_binary)" || exit 2
pixir_report_binary
"$PIXIR_BIN" doctor --json
The report prints the chosen absolute path and version to stderr, identically
in fanout and steer. Quote "$PIXIR_BIN" for invocation so paths with spaces
work. All pixir commands below are shorthand for that selected binary.
Never auto-build, auto-install, alter global PATH, or change to the skill
checkout. Use the caller workspace for session lookup and relative artifacts.
What ships with it
5 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 Changed · +35 lines 7e122f80336b
- 2mo ago First seen · 303 lines · 126 tokens per session scan A adce9ad3cac1
pixir-delegate is a skill published in the GitHub repository Ranvier-Technologies/pixir (24 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 4,827 once invoked, about $0.0005 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 2026-08-30.
pixir-delegate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pixir-delegateRanvier-Technologies/pixir | Skill | 24 | 1mo ago | MIT | A | 126 | Claude Code |
| elixirericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 72 | Claude Code, Codex |
| elixir-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 47 | Claude Code |
| repo-harness-assessmentyfge/agent-harness-skills | Skill | 12 | 2d ago | MIT | A | 56 | Claude Code |
| repo-contracts-and-boundariesyfge/agent-harness-skills | Skill | 12 | 2d ago | MIT | A | 41 | Claude Code |
| work-state-and-deliveryyfge/agent-harness-skills | Skill | 12 | 2d ago | MIT | A | 48 | Claude Code |
| runtime-evidence-and-tracingyfge/agent-harness-skills | Skill | 12 | 2d ago | MIT | A | 39 | Claude Code |