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/d-o-hub/github-template-ai-agents/delegatenpx skills add d-o-hub/github-template-ai-agents --skill delegategit clone --depth 1 https://github.com/d-o-hub/github-template-ai-agentsWrote 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/d-o-hub/github-template-ai-agents/delegate)<a href="https://agentmods.dev/skills/d-o-hub/github-template-ai-agents/delegate"><img src="https://agentmods.dev/badge/skills/d-o-hub/github-template-ai-agents/delegate.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 | $0.00063 | $0.00729 |
| Opus 5 | $0.00032 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate Skill
The Delegate skill provides a lightweight tier for rapid retrieval and context gathering.
When to Use
- Quick context lookups and pattern matching
- Finding specific code implementations or documentation
- Assessing the current state of a repository before planning
- Identifying potential areas for modification without deep analysis
- Even if they just say "find where X is defined" or "what's the current state of Y"
Workflow
- Context Retrieval: Use
grepandglobto locate files matching the query. - Summarization: Read relevant files and synthesize findings into a concise summary.
- Handoff: Pass gathered context to the primary agent or an Implementer.
What to Retrieve
| Query Type | Tools | Example |
|---|---|---|
| "Where is X defined?" | grep -rn "def X|class X|function X" |
Find function/class definitions |
| "What uses X?" | grep -rn "import X|require.*X|from X" |
Find all consumers of a module |
| "Show me the structure" | find . -type f -name "*.py" | head -30 |
Map directory layout |
| "What changed recently?" | git log --oneline -10 |
Recent commit history |
| "What's in this config?" | Read the file directly | Parse configuration files |
When to Hand Off
Delegate should hand off to an Implementer when:
- The task requires modifying code, not just reading it
- The user's intent is clearly "fix" or "change" rather than "find" or "show"
- The retrieved context reveals a bug or issue that needs a code fix
Gotchas
- Avoid deep file reads when a targeted grep would suffice — saves tokens and context.
- When searching for patterns, use the narrowest regex possible to avoid noise.
- If the query is ambiguous, retrieve first, then ask for clarification with context.
Rationalizations
| Rationalization | Reality |
|---|---|
| "I can find this faster myself" | Using the Delegate skill ensures systematic coverage and reduces cognitive load during discovery. |
| "Just grep for it inline" | Structured retrieval with handoff ensures findings are captured and passed to the right agent. |
What ships with it
1 file 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.
- 3d ago First seen · 75 lines · 63 tokens per session scan A 8c963b83478c
delegate is a skill published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 729 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 2026-08-31.
Other skills, from other repositories
omh-image-cards
This is a Hermes-native img-summary workflow skill.
omh-accessibility-audit
This is a Hermes-native accessibility-audit workflow skill.
omh-backend
This is a Hermes-native backend workflow skill.
omh-design-quality-gate
This is a Hermes-native design-quality-gate workflow skill.
omh-failure-signal-audit
This is a Hermes-native failure-signal-audit workflow skill.
omh-agent-board
This is a Hermes-native agent-board workflow skill.