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/gvkhosla/pi-tinker/copilot-instructionsgit clone --depth 1 https://github.com/gvkhosla/pi-tinkerWrote 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/gvkhosla/pi-tinker/copilot-instructions)<a href="https://agentmods.dev/instructions/gvkhosla/pi-tinker/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/gvkhosla/pi-tinker/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 | $0.00215 | $0.00215 |
| Opus 5 | $0.00108 | $0.00108 |
| Sonnet 5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
pi-tinker 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.
What it actually says
pi-tinker repository instructions
- Read
AGENTS.mdanddocs/coding-agents.mdbefore changing workflows. - Pi is the primary UI; shell-based agents can run
node scripts/agent-cli.mjs <subcommand>. - Use official Tinker SDK, Tinker Cookbook, and
tml-renderers; do not create a parallel training framework. - Keep generated Python and data files normal, editable, and inspectable.
- Default to
thinkingmachines/Inkling; preserve support for explicitly selected alternative Tinker models. - For Inkling, use Python 3.11+, Tinker SDK 0.23+, and
tinker-cookbook. - Match baseline and checkpoint reasoning effort. Default Inkling SFT/eval effort is
0.9unless the user deliberately changes it. - Never trigger API usage or training without explicit approval. Smoke-test for two steps before scaling.
- Use
@trigger.dev/sdkv4 patterns if unrelated Trigger.dev code is encountered; never use deprecatedclient.defineJob.
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 · 12 lines · 215 tokens per session scan A ec84b34d43c2
pi-tinker copilot-instructions.md is an instructions file published in the GitHub repository gvkhosla/pi-tinker (24 stars, last pushed 7d ago), licensed Apache-2.0. It adds 215 tokens to every session, about $0.0011 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
axolotl AGENTS.md
AGENTS.md instructions for axolotl-ai-cloud/axolotl, covering axolotl, tech stack, commands, training methods and config pattern.
pi-commandcode-provider AGENTS.md
AGENTS.md instructions for patlux/pi-commandcode-provider, a project described as: pi custom provider for the Command Code API — 18 models including Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, and Qwen.
tuning-engines-cli CLAUDE.md
Instructions for cerebrixos-org/tuning-engines-cli, covering tuning engines mcp server, setup, claude desktop configuration, claude code and available tools.
LLM-Wiki AGENTS.md
Instructions for VectorPeak/LLM-Wiki, covering obsidian second brain - codex cli operating manual, how to operate, command routing tables (grouped by category), wiki layer - simplified knowledge operations and vault - daily writing, capture, find.
axolotl CLAUDE.md
Claude Code instructions for axolotl-ai-cloud/axolotl, a project described as: Go ahead and axolotl questions.
cavegemma AGENTS.md
AGENTS.md instructions for JuliusBrussee/cavegemma, covering agents.md, what this project is, what "caveman" means in code, pipeline at a glance and specific traps (each cost real hours / $).