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 SkillMedev/skills --skill decision-makinggit clone --depth 1 https://github.com/SkillMedev/skillsWrote 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/skillmedev/skills/decision-making)<a href="https://agentmods.dev/skills/skillmedev/skills/decision-making"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/decision-making/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/skillmedev/skills/decision-making"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/decision-making.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00128 | $0.01665 |
| Opus 5.5 | $0.00051 | $0.00666 |
| Sonnet 5.5 | $0.00026 | $0.00333 |
| Haiku 4.5 | $0.00013 | $0.00167 |
Grade A, and why
decision-making 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 11d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Making
Most bad decisions are not caused by bad reasoning - they are caused by deciding the wrong question, rationalizing a pre-chosen favorite, or spending a week of analysis on a choice that could be undone in an afternoon. This process matches the depth of analysis to the stakes, forces criteria to be written before options are scored, and leaves a journal entry so judgment can be calibrated later.
Operating procedure
Order matters: classification comes first because it decides whether the rest of the process runs at all, and criteria must be locked before any option is scored - scoring first invites rationalizing a favorite.
Step 1: Gather inputs
Collect before analyzing. Label any estimate the user cannot source as a guess.
- The decision, stated in one sentence with a deadline. Default deadline if none exists: set one now - endless analysis is itself a costly choice.
- The real options on the table. Push for at least three; a binary framing usually hides a third option (negotiate, delay, pilot, partial commitment).
- What happens if the user does nothing (the status quo is always an option and often the silently chosen one).
- Constraints that are truly fixed vs. merely assumed.
- The user's emotional state (tired, rushed, angry, infatuated with one option) - record it; it belongs in the journal entry.
Step 2: Classify reversibility
- Two-way door (reversible, low stakes): decide fast and move on. Rule of thumb: if undoing the choice costs less than a day of effort, spend minutes, not days. Decide with roughly 70% of the information you wish you had - waiting for 90% means you were slow.
- One-way door (irreversible or high stakes - quitting a job, relocating, marriage, shutting down a product): run Steps 3-8 in full.
Say which classification applies and why before proceeding.
Step 3: Frame the real question
State precisely what is being decided, what problem it solves, and whether that is the right problem. Surface hidden assumptions ("this assumes the promotion won't come through - is that confirmed?").
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.
- 11d ago Changed · +2 lines e693681944f0
- 1mo ago First seen · 110 lines · 128 tokens per session scan A 98a6b466711e
decision-making is a skill published in the GitHub repository SkillMedev/skills (19 stars, last pushed 3d ago), licensed MIT. It adds 128 tokens to every session and 1,665 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
webinar-funnel-builder
Designs a complete webinar funnel - registration page promise, reminder email sequence timed against typical 35-45 percent show-up rates, webinar structure with a 70 percent teach / 30 percent offer split and the pivot script, replay window and urgency rules, and the post-webinar email sequence - with a funnel-metrics…
youtube-script-writer
Writes retention-engineered long-form YouTube scripts on a hook/body/payoff architecture - a first-30-seconds hook that survives the retention cliff, a beat-sheet body with mini-hooks and bridges, timed pattern interrupts, and a payoff that over-delivers - with B-roll and editing cues marked inline. Use when someone…
show-notes-writer
Produces complete podcast show notes from a transcript or episode outline - a standalone summary block, timestamped chapters that name what happens, screenshot-worthy key takeaways, guest bio, curated links, and keyword placement for search. Use when someone says "write show notes for this episode", "turn this…
systematic-review
Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a…
policy-brief
Writes a concise, evidence-based policy brief - problem, options compared on consistent criteria, and a recommendation - that a decision-maker can act on in minutes. Use when someone asks "write a policy brief", "summarize the evidence and options for this decision", "brief the minister/board/council on X", or needs a…
thumbnail-concept
Produces three distinct high-CTR YouTube thumbnail concepts per video - each a full spec with focal point, precise facial-expression direction, text overlay copy, color and background direction, and two paired title variants. Use when someone says "I need a thumbnail idea", "why is my CTR low", "help me pick a…