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 fatihguner/foreman --skill choosing-and-executinggit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/choosing-and-executing)<a href="https://agentmods.dev/skills/fatihguner/foreman/choosing-and-executing"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/choosing-and-executing.svg" alt="Measured on agentmods" 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 | $0.00118 | $0.03903 |
| Opus 5 | $0.00059 | $0.01951 |
| Sonnet 5 | $0.00024 | $0.00781 |
| Haiku 4.5 | $0.00012 | $0.00390 |
Grade A, and why
choosing-and-executing 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Choosing and Executing
The cost of searching for the perfect decision almost always exceeds the cost of making a "good enough" one and iterating. Scott McNealy, cofounder of Sun Microsystems, captured this asymmetry in a single observation: he spent far less energy worrying about making the right decision and far more ensuring that any decision he made turned out right. The distinction is not semantic. It relocates agency from the moment of choice -- where the entrepreneur has minimal control over future variables -- to the months of execution that follow, where nearly everything is within reach. Founders who internalise this shift stop treating decisions as bets to be perfected and start treating them as hypotheses to be tested, adapted, and driven to outcomes through disciplined follow-through.
The Toolkit
Technique 1: The Reversibility Test
Not all decisions deserve equal deliberation. Jeff Bezos famously divided choices into "one-way doors" (irreversible, high-stakes) and "two-way doors" (reversible, correctable). Most entrepreneurial decisions fall through the second door -- yet founders routinely treat them as though they are signing a blood oath.
The diagnostic question: If this decision proves wrong in six months, can the company course-correct without catastrophic loss? If yes, the decision is a two-way door. Make it quickly, monitor outcomes, and adjust.
Why founders over-deliberate on two-way doors:
- Identity attachment. The choice feels like it defines the founder, not just the venture.
- Anxiety amplification. Research by Francesca Gino demonstrates that anxiety makes people simultaneously more receptive to advice and less capable of distinguishing good advice from bad -- a dangerous combination that extends deliberation without improving quality.
- Perfectionism as procrastination. Waiting for the "objectively correct" answer is often a socially acceptable form of avoidance.
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 Changed · +247 lines · +118 tokens per session aa4826a16999
- 8d ago First seen · 1 lines · 0 tokens per session scan A 6094eded5dec
choosing-and-executing is a skill published in the GitHub repository fatihguner/foreman (47 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 3,903 once invoked, about $0.0006 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
threshold
Gates commitment on irreversible decisions by measuring reversal cost and enforcing proportional exploration depth.
ai-loop
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
war-room
Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions. Use when reversibility score is low and adversarial review is warranted.
project-execution
Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement.
software-implementation
Write the minimal production code needed to make failing TDD tests pass (Green phase of red-green-refactor). Use when failing tests exist and production code must be written or modified to satisfy them. Reads and interprets failing test output, discovers codebase conventions (module layout, naming, import patterns…
war-room-checkpoint
Assesses decision reversibility and risk at critical checkpoints. Use when a workflow reaches a high-stakes branch needing escalation check.