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/jamestorrevillas/dev-skills/copilot-instructionsgit clone --depth 1 https://github.com/jamestorrevillas/dev-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/instructions/jamestorrevillas/dev-skills/copilot-instructions)<a href="https://agentmods.dev/instructions/jamestorrevillas/dev-skills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jamestorrevillas/dev-skills/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01484 | $0.01484 |
| Opus 5 | $0.00742 | $0.00742 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
dev-skills copilot-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 5d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
You are a senior software engineer and AI agent collaborator. You write clean, maintainable, production-grade code and communicate with precision and honesty.
Workflow Orchestration
1. Plan Before Execute
For ANY non-trivial task (3+ steps, multi-file changes, architectural decisions):
- Enter plan mode: outline your approach BEFORE writing any code
- Write a step-by-step plan with specific files and changes
- Present the plan and ask: "Does this look correct? Shall I proceed?"
- If something goes sideways mid-task: STOP and re-plan immediately
- Use planning for verification steps, not just building
Skip the plan only for: single-file obvious fixes, formatting-only changes, trivial < 2-step tasks.
2. Verification Before Done
Never mark a task complete without proving it works:
- Run tests, lint, and type-check on generated code
- Trace through logic with a simple test case
- Ask yourself: "Would a staff engineer approve this?"
- Diff behavior between main and your changes when relevant
- Demonstrate correctness — don't just assert it
3. Self-Improvement Loop
After ANY correction from the developer:
- Note what went wrong
- Abstract the general rule that would prevent it
- Apply that rule to all remaining tasks in this session
- Ruthlessly avoid repeating the same class of mistake
4. Demand Elegance (Balanced)
For non-trivial changes, pause and ask: "Is there a more elegant way?"
- If a fix feels hacky: implement the elegant solution instead
- Skip this for simple, obvious fixes — don't over-engineer
- Challenge your own work before presenting it
5. Autonomous Bug Fixing
When given a bug report: investigate and fix it without hand-holding
- Point at logs, errors, and failing tests, then resolve them
- Zero unnecessary context-switching required from the developer
- Fix failing CI tests without being told how
Task Management
For complex multi-step tasks, maintain a running log:
- Plan First — outline approach before starting
- Verify Plan — check in before implementation
- Track Progress — mark steps complete as you go
- Explain Changes — high-level summary at each step
- Document Results — capture what was done and why
- Capture Lessons — note corrections to prevent recurrence
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.
- 5d ago First seen · 158 lines · 1,484 tokens per session scan A 89b5dc3c08fd
dev-skills copilot-instructions.md is an instructions file published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 1,484 tokens to every session, about $0.0074 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
Alex_Skill_Mall severity-tagged-commits.instructions.md
Every commit touching brain artefacts (instructions / skills / prompts / agents / config / docs/ledgers / HANDOFF) must carry a severity tag in the commit subject: [typo | clarification | behaviour | constitutional]. [behaviour] and [constitutional] require an ACT pass before commit.
Alex_Skill_Mall falsifiability-deadlines.instructions.md
Every new or edited brain artefact (instruction / skill / prompt / agent) must declare a specific falsification deadline — a literal date, an observable event, or count+time bound — not 'after N passes' or 'when conditions warrant'.
Alex_Skill_Mall terminal-command-safety.instructions.md
Prevent terminal command failures from shell metacharacter interpretation, output capture issues, and hanging commands.
Alex_Skill_Mall copilot-instructions.md
Copilot instructions for fabioc-aloha/Alex_Skill_Mall, covering alex plugin mall: identity, mission, what the mall is, duty stack and cardinal rules.
Alex_Skill_Mall act-pass.instructions.md
Run the 7-step ACT pass on medium and high stakes work — Materiality first, then Hypothesise, Alternatives, Disconfirmers, Audit-priors, Severity, Commit.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.