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/peargent/peargent/copilot-instructionsgit clone --depth 1 https://github.com/Peargent/peargentWhat 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 | $0.00617 | $0.00617 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
peargent 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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peargent – PR Review Rules
Goal
Provide concise, high-signal PR reviews for the Peargent Python Agent Framework.
Favor clarity over completeness and summary over inline comments.
One PR = one review comment, unless there is a real bug.
Review Style (STRICT)
- Prefer one high-level summary comment
- Inline comments are allowed ONLY for:
- Bugs
- Security issues
- Broken imports
- Public API breakage
- If the PR is acceptable, say “Looks good” and stop.
Do not behave like a linter.
Comment Size Rules
- Maximum 5 bullet points in a review
- Any explanation longer than 3 lines must be collapsible
<details>
<summary>Details</summary>
Additional context here.
</details>
Do NOT Comment On
- Formatting or style (Black handles this)
- Naming preferences
- Minor refactors
- “Consider adding comments”
- Suggestions already enforced by CI
- Hypothetical improvements
Blocking Rules
Only block a PR if one of these is true:
- Tests fail (
python -m pytest) - Public API is broken
- Internal modules are imported (
peargent._core.*) - Missing type hints on public APIs
- CI fails on supported Python versions
Everything else is non-blocking.
CI Awareness
- Assume CI is authoritative
- Do not restate CI errors unless necessary
- Do not explain test failures unless subtle
Import Rule (CRITICAL)
For User-Facing Code (Examples, Documentation, etc)
✅ MUST use public APIs:
from peargent import create_agent, create_tool, create_pool
from peargent.models import groq, anthropic, openai
❌ FORBIDDEN (blocking):
from peargent._core.agent import Agent
from peargent._core.tool import Tool
For Internal Modules (Built-in Tools, Core Implementation)
✅ SHOULD use private APIs:
from peargent._core.tool import Tool
from peargent._core.agent import Agent
❌ Avoid public API re-exports in internal code.
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.
- 3d ago First seen · 132 lines · 617 tokens per session scan A f69e75becc92
peargent copilot-instructions.md is an instructions file published in the GitHub repository Peargent/peargent (82 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 617 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
timbal CLAUDE.md
Instructions for timbal-ai/timbal, covering claude.md, commands, development and testing, benchmarks and repository layout.
agentcontrolplane CLAUDE.md
Claude Code instructions for humanlayer/agentcontrolplane, covering agent control plane (acp) - ai assistant instructions, 🚨 the 1500-line minimum read rule - this is not optional, 📋 your 20-point todo list - you need this structure, current todo list (you must maintain 20+ items) and 🚨 mandatory persona selection.
hyperframes AGENTS.md
AGENTS.md instructions for heygen-com/hyperframes, covering hyperframes, skills, build & test, linting & formatting and composition validation.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
jesse AGENTS.md
Instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.