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 hristo2612/jinn --skill delegationgit clone --depth 1 https://github.com/hristo2612/jinnWrote 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/hristo2612/jinn/delegation)<a href="https://agentmods.dev/skills/hristo2612/jinn/delegation"><img src="https://agentmods.dev/badge/skills/hristo2612/jinn/delegation/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/hristo2612/jinn/delegation"><img src="https://agentmods.dev/badge/skills/hristo2612/jinn/delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 65 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00017 | $0.00924 |
| Opus 5 | $0.00009 | $0.00462 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
delegation 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 10d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation Skill
Use this skill when another employee or engine is a better fit for a bounded piece of work. Delegate across roles; use native sub-agents only for extra hands inside your own role. Prefer the chain of command for multi-layer work, while keeping every brief and stop condition explicit.
Choose the target
- Use
list_employeesfor the roster,find_employeesto filter by department/rank/engine, andget_employeeto inspect persona, manager, and direct reports. - Select by role and persona fit, not novelty or a desire to spread work around. One employee can have several parallel sessions.
- Delegate through the relevant manager when they should own decomposition and review. Direct delegation remains valid when it is the clearest route.
Tracked work versus a quick session
Use delegate_task for company work that needs ownership, status, review, or a durable record. One call uses or mints the Todo, starts the child session, and links them:
{
"employee": "a-builder",
"title": "Implement parser validation",
"task": "Implement the specified validation. Acceptance: focused tests fail before the change, then the focused and full suites pass. Report changed files and command evidence.",
"effortLevel": "medium",
"idempotencyKey": "parser-validation-v1"
}
- Pass
workItemIdwhen an existing Todo already tracks the outcome. - Use one stable
idempotencyKeyfor retrying the same delegation. If a spawn fails after the Todo is minted, preserve and report the returned work-item id; do not blindly create another delegation. - If you pass
attachments, every entry must be a managed file ID returned bylist_files— never workspace or absolute paths. Missing or stale managed file IDs are rejected before Jinn creates the Todo or child session. Attach only files the child genuinely needs.
Use spawn_session for a quick, untracked question or short consultation:
{
"employee": "a-reviewer",
"prompt": "Review this schema choice and return the top two concrete risks. Do not modify files."
}
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.
- 10d ago First seen · 72 lines · 17 tokens per session scan A 72d8a3132067
delegation is a skill published in the GitHub repository hristo2612/jinn (315 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 924 once invoked, about $0.0001 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.