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/transcendr/pi-goals/agents-mdgit clone --depth 1 https://github.com/transcendr/pi-goalsWrote 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/transcendr/pi-goals/agents-md)<a href="https://agentmods.dev/instructions/transcendr/pi-goals/agents-md"><img src="https://agentmods.dev/badge/instructions/transcendr/pi-goals/agents-md.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 | $0.01191 | $0.01191 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
pi-goals AGENTS.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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — pi-goals
Project: project-local Pi extension implementing pi-goal.
Primary code: .pi/extensions/goal/.
Canonical planning/research:
.ai/issues/.ai/docs/codex-goal-command-research.md.ai/.pi-goals/
Extension architecture
Keep the extension modular. Current module map is documented by file names in .pi/extensions/goal/; preserve separation between entrypoint, command/tools, lifecycle/runtime, state/telemetry, prompts, UI/widget, monitor, and shared domain helpers.
Required quality gate
Before substantial implementation:
sentrux gate --save .pi/extensions/goal
After implementation, run the single required gate:
npm run gates:quality
This runs Sentrux gate/check, slop guard, TypeScript validation, and Pi extension load validation.
Rules:
- Run Sentrux against
.pi/extensions/goal, not repo root. - Fix Sentrux degradation/rule failures unless the user explicitly accepts the tradeoff.
- Do not use TypeScript escape-hatch casts in
.pi/extensions/goal, especiallyas unknown asoras any.
Repo artifact hygiene
Do not add repo-tracked docs, validation notes, design notes, or closeout/result files unless they will be read, maintained, or used by future work.
Default ephemeral evidence to /tmp (for example live-probe transcripts, debug logs, one-off summaries, command captures). Keep durable repo artifacts only when:
- the user explicitly asks for a repo-tracked file/path;
- an existing project workflow requires the artifact, such as issue workflow docs under
.ai/docs/issue-workflow/...; - the artifact is a reusable test/probe/script that will be run again; or
- the content is necessary long-term documentation, not just proof that this turn happened.
If the likely future use is "probably never", do not write it into the repo. If a user says to "write results" or "record evidence" without specifying a repo path, prefer /tmp or the final response. Ask before creating a new repo artifact when durability is ambiguous.
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 · 101 lines · 1,191 tokens per session scan A 2a62dd18d227
pi-goals AGENTS.md is an instructions file published in the GitHub repository transcendr/pi-goals (25 stars, last pushed 3mo ago), licensed MIT. It adds 1,191 tokens to every session, about $0.0060 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
pi-extensions AGENTS.md
AGENTS.md instructions for narumiruna/pi-extensions, covering repository guidelines, documentation and communication, repository structure, commands and tooling and dependency safety.
cogitator AGENTS.md
Instructions for guilhermehto/cogitator, covering agents.md, layout, commands, demo / readme screenshot and conventions.
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
CodexBar AGENTS.md
AGENTS.md instructions for bob-zebedy/CodexBar, covering repository guidelines, 项目结构与模块组织, 构建、测试与开发命令, 写作风格 and 代码和注释.