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 commands/fatihguner/foreman/execution-commandsgit 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 | $0.00041 | $0.03056 |
| Opus 5 | $0.00020 | $0.01528 |
| Sonnet 5 | $0.00008 | $0.00611 |
| Haiku 4.5 | $0.00004 | $0.00306 |
Grade A, and why
execution-commands 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 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.
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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution Commands
/apply
Description
Applies a single skill to the entrepreneur's current context. This command invokes the skill-executor agent, which loads the specified skill, pulls identity and company data from memory, adapts the framework to the entrepreneur's stage, and produces a structured analysis. Results are persisted to the history layer of memory. An optional stage override forces the skill to operate as though the company were at a different stage — useful for scenario planning.
Syntax
/apply [skill-name] [--stage stage]
Parameters
| Parameter | Required | Type | Default | Description |
|---|---|---|---|---|
skill-name |
Yes | string | -- | Skill identifier in kebab-case (e.g., porters-five-forces) |
--stage |
No | string | from memory | Override the company stage: idea, validation, early-traction, growth, scale |
Examples
/apply porters-five-forces
→ Applying "Porter's Five Forces" to context...
Stage: early-traction (from company profile)
Loading competitive data from memory...
[Full framework analysis output with five forces scored and interpreted]
/apply swot-pest-analysis --stage growth
→ Applying "SWOT-PEST Analysis" with stage override: growth
Note: Company profile indicates "early-traction" — analysis adjusted to growth-stage lens.
[Combined SWOT and PEST analysis with growth-specific guidance]
/apply business-model-canvas
→ Applying "Business Model Canvas" to context...
Stage: idea (from company profile)
[Nine building blocks populated from company context, gaps identified]
/apply stoic-emotional-mastery
→ Applying "Stoic Emotional Mastery" to context...
Stage: validation (from company profile)
[Framework applied to current active challenges from memory]
Related Commands
/skill [name]— Preview a skill's summary before applying it/skills— Browse available skills to find the right one/output [template] [audience]— Format the analysis results for a specific audience
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 · 325 lines · 41 tokens per session scan A e7b4ffafe487
execution-commands is a command published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 3,056 once invoked, about $0.0002 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 commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
sdlc-implement
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.
ghost-decode
Decode a ghost-font video and reveal the hidden text.
doctor
Check the Modellix CLI install, credential resolution, API connectivity, and balance.
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.
arckit.adm-preliminary
Set ADM scope, architecture vision, drivers, constraints, and success criteria.