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/clear-frameworknpx skills add tupe12334/instinct --skill clear-frameworkgit 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 | $0.00024 | $0.01772 |
| Opus 5 | $0.00012 | $0.00886 |
| Sonnet 5 | $0.00005 | $0.00354 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
clear-framework 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clear Goals
Overview
clear is a goal-setting framework designed for fast-moving, collaborative environments where smart goals can feel too rigid. Developed by Adam Kreek. clear emphasizes team alignment, emotional engagement, and adaptability.
| Letter | Criterion | Core principle |
|---|---|---|
| C | Collaborative | Goals should involve the team, not be handed down |
| L | Limited | Constrained scope and timeline; focus beats ambition |
| E | Emotional | Goals connect to something people care about |
| A | Appreciable | Break large goals into smaller achievable steps |
| R | Refinable | Goals can and should be updated as circumstances change |
Criterion Breakdowns
C — Collaborative
Goals set with the team, not for the team. Collaboration drives ownership, surfaces blind spots, and improves commitment.
In practice:
- Involve key contributors in defining the goal
- Ensure each person can see their role in achieving it
- Shared authorship = shared accountability
Test: Did the people responsible for this goal help shape it?
L — Limited
Focus is finite. Goals that are too broad, long, or numerous dilute attention and energy.
Two dimensions:
- Scope: narrowed to what matters most (not a wish list)
- Time: short enough to stay relevant (3 months is usually better than 12 for operational goals)
Test: If the team had to work on only this for the next period, would it be the right use of their time?
E — Emotional
People execute better on goals that connect to something they care about — purpose, growth, impact, recognition.
In practice:
- Link the goal to team or personal values
- Make the "why" explicit and inspiring
- An emotionally resonant goal survives friction; a purely rational one often doesn't
Test: If someone asked "why does this matter?", does the answer energize or bore?
A — Appreciable
Large goals are overwhelming. Break them into milestones that feel achievable within the current sprint or week.
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 · 152 lines · 24 tokens per session scan A a58e2d51cc79
clear-framework is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 1,772 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-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.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.