Borrowing it
Nothing to install: this file belongs to myICOR/myPKA. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/myICOR/myPKA/main/AGENTS.mdgit clone --depth 1 https://github.com/myICOR/myPKAWrote 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/myicor/mypka/agents-md)<a href="https://agentmods.dev/instructions/myicor/mypka/agents-md"><img src="https://agentmods.dev/badge/instructions/myicor/mypka/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/myicor/mypka/agents-md"><img src="https://agentmods.dev/badge/instructions/myicor/mypka/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04198 | $0.04198 |
| Opus 5.5 | $0.01679 | $0.01679 |
| Sonnet 5.5 | $0.00840 | $0.00840 |
| Haiku 4.5 | $0.00420 | $0.00420 |
Grade A, and why
myPKA 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 1mo 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - myPKA
myPKA (My Personal Knowledge Assistance) is an architectural concept for agentic AI work, not a methodology: the AI team, its contracts, procedures, scripts and work continuity. It works on the content of an ICOR for Life folder, unpacked inside it (mode A) or as a sibling folder (mode B).
This is the canonical, runtime-independent entry contract and the only
entry file. Read it first, every session. Root AGENT.md points here for
compatibility and carries no rules. Per-specialist
06 AI Team/Agents/<Name>/AGENT.md files remain individual role
contracts, not copies of this root contract. How each host finds this
file: "Host notes" below.
If this runtime does not automatically discover these instructions, the
user can paste ADAPTER-PROMPT.md to initialize it. Read the files before
claiming initialization; never replace this contract with generated /init
output. Respect the runtime's higher-priority instructions and permissions.
Runtime capabilities
The myPKA architecture is independent of the model or app. File access, command execution, integrations and isolated subagents are capabilities of the host runtime, not capabilities that a markdown file creates. At first initialization report which are actually available. If a file or tool is unavailable, name the specific gap and continue the supported work; never claim to have read, executed or saved something you could not access.
Use the host's supported dispatch mechanism, passing the assigned specialist's contract and task context. A dispatched specialist keeps its assigned identity instead of reinitializing as Larry. Without isolated dispatch, offer an explicit manual specialist handoff; never pretend independent subagents ran. A chat-only interface needs the relevant files supplied explicitly and cannot persist changes without a file tool.
The harness layer is generated, not written by hand. Skills, agent shims,
hook configs and host settings (.gemini/settings.json,
.codex/config.toml) are built from the vault's own frontmatter by
06 AI Team/AI Team Knowledge/Scripts/scaffold-init.py. A skill is a
pointer: it names its SOP and carries no procedure text, so the SOP stays
the single body of every procedure. Guards run as hooks on hosts that have
hooks, and are prose rules you follow yourself on hosts that do not. Dot
folders (.claude/, .codex/, .cursor/) are per device and per host,
never the source of truth: delete one and re-run the generator. The model
announces the command; you run it. Nothing here auto-launches, with one
exception: the hire scripts named in
[[SOP-1007-hire-a-new-agent|SOP-1007]] ("Scripts Nolan runs in a hire"),
which Nolan runs from the vault root and reports; that section is the
closed list and the only place the exception is defined.
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.
- 1mo ago Changed · +1 lines · +25 tokens per session 212d9d6517b9
- 1mo ago Changed · +57 lines · -915 tokens per session 7dddf752e4ec
- 1mo ago First seen · 239 lines · 5,088 tokens per session scan A 82f367e8f11d
myPKA AGENTS.md is an instructions file published in the GitHub repository myICOR/myPKA (318 stars, last pushed 22d ago), licensed MIT. It adds 4,198 tokens to every session, about $0.0168 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.