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 skills/tupe12334/instinct/star-methodnpx skills add tupe12334/instinct --skill star-methodgit clone --depth 1 https://github.com/tupe12334/instinctWhat 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 | $0.00023 | $0.01972 |
| Opus 5 | $0.00012 | $0.00986 |
| Sonnet 5 | $0.00005 | $0.00394 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
star-method 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 yesterday.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
star Method
Overview
star is a four-part narrative structure for communicating past experiences or case studies with precision and impact. Each element builds on the last: context sets the scene, task pins accountability, action shows what you did, result proves it worked.
┌─────────────────────────────────────────────────────────┐
│ S ──► T ──► A ──► R │
│ │
│ Situation Task Action Result │
│ (context) (your (steps (measurable │
│ role) taken) outcome) │
└─────────────────────────────────────────────────────────┘
Use star in behavioral interviews, performance reviews, retrospectives, case study presentations, and any situation where "trust me, I handled it" is not enough.
Element Breakdowns
S — Situation
Set the scene with just enough context for the listener to understand what was at stake.
Include:
- What was happening and why it mattered
- The scale or scope (team size, revenue at risk, timeline pressure)
- Any constraints the audience needs to evaluate your response
Keep it to 1–3 sentences. Do not editorialize — state facts.
Bad: "Things were pretty chaotic and nobody knew what to do." Good: "Our production database went down during peak traffic, affecting 40,000 active users and threatening $200K in same-day revenue."
T — Task
State your specific responsibility. This separates what the situation demanded from what you were accountable for.
Include:
- Your role or title at the time
- What was explicitly expected of you
- Any competing priorities or constraints you personally faced
Bad: "I needed to fix things." Good: "As on-call engineer, I was responsible for restoring service within our 30-minute SLA while keeping the support team informed."
A — Action
The most important section. Detail the steps you personally took — not "we did."
Structure:
- First action and rationale
- Pivots or decisions made under uncertainty
- How you handled obstacles or involved others
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.
- yesterday First seen · 157 lines · 23 tokens per session scan A e0ad1f3c8c71
star-method is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 23 tokens to every session and 1,972 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-opportunity-cost
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-circle-of-competence
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.