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 instructions/dev-lou/pixelpilot/reasoninggit clone --depth 1 https://github.com/dev-lou/PixelPilotWhat 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 | $0.02073 | $0.02073 |
| Opus 5 | $0.01037 | $0.01037 |
| Sonnet 5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
PixelPilot reasoning.instructions.md 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reasoning — Meta-Skill 2026
Structured thinking protocol: restate → constrain → diverge → evaluate → propose → review. Never write a line of code until all six steps are complete.
WHY THIS EXISTS
AI models are pattern-matchers. Without a forcing function they will:
- Jump to the most common solution (which may be wrong for this context)
- Miss implicit constraints (auth model, existing tech debt, team conventions)
- Generate confident but incorrect code in unfamiliar domains
- Fail to surface the ambiguity that a human expert would immediately flag
This skill installs that forcing function.
THE SIX-STEP REASONING WORKFLOW
Run every step in order. Do not skip. Do not merge steps.
STEP 1 — RESTATE THE GOAL
Paraphrase the request in your own words. Be specific. Include:
- What the user wants to achieve (outcome, not activity)
- Who is the end user or beneficiary
- What success looks like (measurable if possible)
- What is explicitly out of scope (if stated)
Example restatement:
"The user wants a multi-step checkout form for an e-commerce site (Premium Modern
design language). Success = user can complete purchase in < 90 s on mobile.
Out of scope: payment processing logic — only the UI layer."
If the restatement changes what the user seemed to ask for, stop and confirm before continuing.
STEP 2 — LIST ALL CONSTRAINTS
Enumerate every constraint, grouped by category. Ask clarifying questions for anything marked [?].
## Constraints
### Technical
- Framework: Next.js 14 App Router [confirmed / ?]
- Styling: Tailwind v4 + CSS custom properties [confirmed / ?]
- Browser support: modern evergreen + Safari 16+ [?]
- Must work without JS? (progressive enhancement) [?]
### Design System
- Design language: Premium Modern [confirmed / ?]
- Tokens already defined in tokens.css? [confirmed / ?]
- Dark mode required? [confirmed — law #6]
### Business / Product
- Must ship by: [?]
- Analytics / tracking requirements? [?]
- Legal / compliance (GDPR, WCAG, HIPAA)? [?]
### Team
- Will other devs maintain this? Skill level? [?]
- Existing component library to reuse? [?]
- PR / code review process affects scope? [?]
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 · 263 lines · 2,073 tokens per session scan A 999a3b33de3f
PixelPilot reasoning.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,073 tokens to every session, about $0.0104 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 instructions, from other repositories
arai CLAUDE.md
Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.
healthcare-agents AGENTS.md
Instructions for ajhcs/healthcare-agents, covering healthcare agents repository instructions, repository map, git workflow and self-improvement loop.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.
shenzjd-skills CLAUDE.md
Claude Code instructions for wu529778790/shenzjd-skills, covering claude.md, project overview, commands, a single skill's unit test and architecture.
ui-ux-design-pro-skill CLAUDE.md
Instructions for saifyxpro/ui-ux-design-pro-skill, covering project overview, cli commands, full design system generation (markdown output), search across all databases (sub-50ms) and audit ui code quality.
syncai copilot-instructions.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.