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/justguy/hoplon/agents-mdgit clone --depth 1 https://github.com/justguy/hoplonWhat 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 | $0.00512 | $0.00512 |
| Opus 5 | $0.00256 | $0.00256 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
hoplon 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
These instructions apply to the entire repository.
Start here
Read:
README.mdHOPLON_VISION.mdARCHITECTURE.mdCONTRIBUTING.md
Working method
Use TRACE -> REPORT -> FIX -> PROVE:
- Trace the complete data path and identify the writer, consumer, enforcement point, and lifecycle of every changed contract.
- Report the observed behavior and the weakest link before changing code.
- Fix the smallest complete slice; do not add parallel mechanisms.
- Prove the claimed behavior through a real operation, session, handler, or transport path.
Architecture rules
- Environment access belongs behind injected adapters.
- Hoplon never owns model selection, retry, escalation, or approval policy.
- Deterministic
PASS/BLOCKauthority uses manifest, path, snapshot, and AST facts only. - Advisory providers must report unavailable or degraded states honestly and cannot silently change deterministic verdicts.
- Imports flow from engine and operations toward adapters/contracts/pure utilities, never toward a host orchestrator.
- Use named ES-module exports, strict TypeScript, and
async/await. - Keep every TypeScript file under
src/hoplonat or below 300 lines. - Do not truncate agent-facing evidence with arbitrary character caps.
- Avoid new defaults, thresholds, or blocking behavior unless the change is explicit, justified, documented, and supported by an adversarial corpus.
Tests
- Bug fixes require a regression test that reproduces the failure.
- Contract changes require producer and consumer coverage.
- Runtime claims require a real handler, dispatch, session, or flow test.
- Prefer the narrow Vitest file or directory that owns the changed surface.
- Run
npm run test:archfor architecture changes andnpm run test:prooffor deterministic kernel changes. - Tests must inject filesystem, versioning, snapshot, lock, provider, and behavior-runner dependencies rather than relying on ambient services.
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 · 60 lines · 512 tokens per session scan A 29763b8109cc
hoplon AGENTS.md is an instructions file published in the GitHub repository justguy/hoplon (0 stars, last pushed 9d ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
tree-sitter-fsharp AGENTS.md
Instructions for ionide/tree-sitter-fsharp, covering improving the f# tree-sitter parser, project structure, running the cli, workflow for adding a new feature and 1. create a test case first.
tree-sitter-analyzer CLAUDE.md
Instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
code-context AGENTS.md
Instructions for infino-ai/code-context, covering code-context: notes for ai agents, project overview, repo map, build, test, gates and conventions.