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/fergius-engineering/instincts/using-instinctsnpx skills add Fergius-Engineering/instincts --skill using-instinctsgit clone --depth 1 https://github.com/Fergius-Engineering/instinctsWhat 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 | $0.00019 | $0.01072 |
| Opus 5 | $0.00010 | $0.00536 |
| Sonnet 5 | $0.00004 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
using-instincts 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
superpowers is the base process: brainstorm, spec, plan, TDD, verify. instincts is one level finer — a set of working reflexes that keep that process honest rather than just followed. This skill is the map to them.
The rule
Load an instinct with the Skill tool the first time it applies in a session — before you act on it, then follow the skill you loaded. If several instincts hit the same move, load them all in one response.
Once loaded, a skill stays active for the rest of the session: apply it without re-invoking. One exception — after a context compact, if you can no longer see the skill's full text, it's gone; reload it before relying on it.
Acting on an instinct that was never loaded this session is working from memory, and it doesn't count: you lose the current text and the checklist, and nothing shows the reflex ran — exactly how corners get cut. Nothing runs until you call the Skill tool. The load is once per skill per session; the cost argument is spent.
| Rationalization | Reality |
|---|---|
| "I applied it internally — same result" | If it was never loaded this session, you worked from memory, not the current text. No checklist, no trace. |
| "The map line below tells me enough" | The map routes, it doesn't teach. The method lives in the skill. |
| "Loading it won't change what I'm about to type" | Then it costs seconds and confirms you. When it would have changed something — that's the whole point. |
| "No time for ceremony right now" | One load per skill per session, seconds each. You'll spend longer justifying the skip. |
| "I loaded it earlier" — said after a compact | If you can't see its full text anymore, it's gone. Reload before relying on it. |
| "superpowers already forces skills, so these are covered" | Not covered — each instinct still gets its own first load. |
| You named an instinct in your reasoning without ever loading it | Naming it is not running it. Load the skill, then proceed. |
User instructions win
User instructions — CLAUDE.md, AGENTS.md, direct requests — take precedence over any instinct here, and instincts take precedence over default behavior. Never cite an instinct against what the user explicitly asked for; skip a skill only when they told you to.
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 · 66 lines · 19 tokens per session scan A 11f727af2a8d
using-instincts is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 1,072 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
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
office-hours
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
echo
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.