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/jsuvic/agent-profile/agents-mdgit clone --depth 1 https://github.com/jsuvic/agent-profileWhat 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 | $0.00939 | $0.00939 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
agent-profile 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 2d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instruction Precedence
If generated and manual instructions conflict, follow the manual project instructions unless they would weaken safety, privacy, or permission limits. Safety, privacy, and explicit deny rules always win.
Project
Name: agent-profile
Description: Local AI-agent setup.
Stack
- Languages: typescript
- Frameworks: None declared
- Package managers: npm
- Testing: None declared
Enabled AI Clients
- Codex
- Claude
Development Workflow
- SDD: Required
- TDD: Required
- Final implementation review: Required
Permissions
| Permission | Mode |
|---|---|
| filesystem read | allow |
| filesystem write | ask |
| shell run | ask |
| dependency install | ask |
| external network | ask |
| secrets access | deny |
| production access | deny |
Safety Rules
- No source-code upload.
- No secret upload.
- No literal tokens in generated configs.
- No telemetry by default.
- No hosted execution in the MVP.
Scope Limits
Cursor, Aider, Copilot, hosted gateways, enterprise RBAC, SIEM integrations, and custom sandbox runtimes are out of scope unless an approved spec adds them.
Completion Checklist
- Run tests.
- Run golden tests when generated files change.
- Run doctor/check once available.
- Review the implementation against the relevant spec.
- List remaining risks or TODOs.
AGENTS.md
Project
This repository implements a local-first AI Agent Profile Compiler.
The tool defines one canonical ai-profile.yaml and compiles it into
agent-specific configuration for Tabnine, Codex, and Claude.
Product Principles
- Local-first by default.
- No source-code upload.
- No secret upload.
- No hosted execution in the MVP.
- Generated files must be deterministic.
- Safety checks are part of the product, not an afterthought.
- Prefer explicit contracts over implicit behavior.
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.
- 2d ago First seen · 167 lines · 939 tokens per session scan A b593ed9fd904
agent-profile AGENTS.md is an instructions file published in the GitHub repository jsuvic/agent-profile (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 939 tokens to every session, about $0.0047 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
image-to-editable-ppt-skill AGENTS.md
Instructions for ningzimu/image-to-editable-ppt-skill, covering agents.md, editing rules, skill documentation architecture, design principles and file responsibilities.
FDEOps AGENTS.md
Instructions for suboss87/FDEOps, covering agents.md - working in the fdeops repository, if you are helping use fdeops in an engagement, if you are contributing to this repository and boundaries.
openai-compatible-imagegen AGENTS.md
Instructions for Syh1906/openai-compatible-imagegen, covering agent instructions, project scope, package management, checks and module boundaries.
sentry-instrumentation AGENTS.md
Instructions for tortastudios/sentry-instrumentation, covering agents guide — sentry-instrumentation, what this repo is, this repo has no "skill registry", if you're a codex agent asked to install this skill and skill-enable block (copy into consumer agents.md).
EduOrchestrate AGENTS.md
Instructions for haroontrailblazer/EduOrchestrate, covering eduorchestrate agent instructions, command and workflow.
arxiv-wiki AGENTS.md
AGENTS.md instructions for synabreu/arxiv-wiki, covering agents.md, project goal and rules.