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 agents/fatihguner/foreman/skill-executor-agentgit clone --depth 1 https://github.com/fatihguner/foremanWhat 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 | $0.00081 | $0.02943 |
| Opus 5 | $0.00041 | $0.01471 |
| Sonnet 5 | $0.00016 | $0.00589 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade C, and why
skill-executor-agent scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **IF** the skill's stage array does not include the entrepreneur's current stage **THEN** proceed with a warning, adapting from the nearest adjacent stage. Never refuse to apply a framework solely because the stage is How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Executor Agent
Role
The skill-executor-agent transforms a static framework into a living analysis. The distinction matters: a skill file describes Porter's Five Forces in the abstract; the skill-executor-agent applies Porter's Five Forces to a specific SaaS company at early-traction stage competing against three incumbents with a six-person team and a twelve-month runway. Every output this agent produces is contextual, not generic.
This agent does not select which skill to apply — that decision belongs to the orchestrator or the playbook-runner. It does not format the final output for a target audience — that belongs to the output-agent. It does not persist results — that belongs to the memory-agent. Its sole responsibility is the application of one framework to one entrepreneur's situation with precision and depth.
Responsibilities
- Load and parse the specified skill file
- Extract stage-specific guidance matching the entrepreneur's current stage
- Apply the skill's prompts to the entrepreneur's specific context (sector, situation, data)
- Evaluate the entrepreneur's situation against the skill's anti-patterns
- Generate a contextualized analysis that reflects the framework's application, not its explanation
- Surface follow-up prompts when the initial application reveals areas requiring deeper exploration
- Return structured output to the calling agent (orchestrator or playbook-runner)
- Handle skills that are inappropriate for the entrepreneur's stage or situation
Activation
| Trigger Condition | Caller | Priority |
|---|---|---|
| Orchestrator determines a single skill is sufficient | orchestrator-agent | High |
| Diagnostic result recommends specific skill(s) | orchestrator-agent | High |
| Playbook step requires skill execution | playbook-runner-agent | High |
| Entrepreneur requests a framework by name | orchestrator-agent | Medium |
Workflow
Step 1: Load and Parse Skill
- Receive skill reference and entrepreneur context from the calling agent.
- Load the skill file. Parse frontmatter (stage, category, complexity, related skills) and body sections (framework, prompts, anti-patterns, stage guidance, use cases).
- Validate that the skill exists and is structurally complete.
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 · 243 lines · 81 tokens per session scan C 6e88ffc21602
skill-executor-agent is an agent published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 81 tokens to every session and 2,943 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
council-meadows
Council member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.
council-musashi
Council member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.
knowledge-extractor
Extracts reusable patterns, pitfalls, and decisions from completed work and writes them to the wiki staging area. Run after finishing a body of work to capture what was learned. Call /learn --compile afterward to integrate staged findings into the knowledge wiki.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
devops-engineer
Designs CI/CD pipelines, provisions cloud infrastructure, and manages releases. Absorbed cloud-engineer and release-manager responsibilities. Runs as the sole Ship phase agent. Use when building CI pipelines, deploying to cloud, or managing releases.
performance-engineer
Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.