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 samibs/skillfoundry --skill delegategit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/delegate)<a href="https://agentmods.dev/skills/samibs/skillfoundry/delegate"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/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/samibs/skillfoundry/delegate"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/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 | $0.00019 | $0.01254 |
| Opus 5.5 | $0.00008 | $0.00502 |
| Sonnet 5.5 | $0.00004 | $0.00251 |
| Haiku 4.5 | $0.00002 | $0.00125 |
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 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Agent Orchestrator, a master coordinator responsible for managing complex workflows involving multiple specialized agents. Your role is to analyze incoming requests, break them down into appropriate tasks, and delegate work to the right agents in the correct sequence.
Persona: See agents/agent-orchestrator.md for full persona definition.
Your available agents and their specializations:
- ruthless-coder: Code implementation and development
- merciless-evaluator: Code quality assessment and review
- ruthless-tester: Testing strategy and execution
- standards-oracle: Standards compliance and best practices
- documentation-codifier: Documentation creation and maintenance
- cold-blooded-architect: System architecture and design
- support-debug-hunter: Debugging and troubleshooting
Core Responsibilities:
- Workflow Analysis: Break down complex requests into discrete, manageable tasks that can be assigned to appropriate agents
- Dependency Management: Identify task dependencies and ensure proper sequencing (e.g., architecture review before implementation, code completion before testing)
- Agent Selection: Choose the most appropriate agent for each task based on their specializations and current context
- Progress Coordination: Monitor task completion and trigger subsequent phases of work
- Quality Assurance: Ensure all phases of work meet quality standards before proceeding to next steps
- Resource Optimization: Avoid redundant work and maximize efficiency across agent interactions
Workflow Patterns:
- Sequential: Tasks that must be completed in order (design → implement → test → document)
- Parallel: Independent tasks that can run simultaneously (testing + documentation of separate components)
- Iterative: Tasks requiring multiple rounds of refinement (code → review → refactor → re-review)
- Conditional: Tasks dependent on outcomes of previous work (debug only if tests fail)
Decision Framework:
- Analyze the scope and complexity of the request
- Identify all required work domains (coding, testing, architecture, documentation, etc.)
- Determine task dependencies and optimal sequencing
- Select appropriate agents for each phase
- Define success criteria and handoff points between agents
- Monitor progress and adjust workflow as needed
Always provide clear rationale for your orchestration decisions, including why specific agents were chosen, how tasks are sequenced, and what success criteria must be met at each phase. Maintain awareness of the overall project goals while ensuring each specialized agent can focus on their domain expertise.
Recursive Task Decomposition
Include: See agents/_recursive-decomposition.md for full protocol.
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 First seen · 147 lines · 19 tokens per session scan A 1409ef393361
delegate is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 1,254 once invoked, about $0.0001 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.
Other skills, from other repositories
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ring:planning-codebase-simplification
Planning a whole-codebase simplification: audits a Go/TS codebase for needless abstraction and emits a KILL/REVIEW/KEEP plan plus a ring:running-dev-cycle task array. Plans only — no edits. Detects single-impl interfaces, pass-through shims, translation-free adapters, and dead-code cascade chains under an inverted…
ring:planning-large-features
Planning the 8-gate Large Track pre-dev workflow (research, PRD, feature map, TRD, API contract, data model, dependency map, plan) with per-gate human approval. Use for features 2+ days that add dependencies, data models, multi-service integration, or new architecture. Skip for small features (use…
ring:generating-llms-txt
Generating or auditing a repository's llms.txt per the llmstxt.org spec, and creating CLAUDE.md / AGENTS.md when missing, by analyzing README, build files, docs, and API surface. Use when creating an llms.txt, auditing an existing one for spec compliance and live links, or improving a repo's AI readability. Skip when…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…