web-capability-compiler AGENTS.md

A project instruction file for coding agents working on the Web Capability Compiler. It identifies the implementation specification, required work order, safety limits, evidence rules, and testing expectations.

In plain words
What is it for?
Use it to guide implementation, testing, schema changes, evidence collection, and decisions about which browser capabilities may be executed.
Why use it?
It gives agents project-specific rules so they know which documents and constraints govern changes. It also prevents unsupported scope expansion and unsafe actions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/maaa2005/web-capability-compiler/agents-md
Clone the repo
git clone --depth 1 https://github.com/Maaa2005/web-capability-compiler

Made for: Codex, OpenCode.

Per session 546 This file is loaded in full into every session.
When invoked 546 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00546 $0.00546
Opus 5 $0.00273 $0.00273
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured yesterday against content hash 2347ad14cac7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-capability-compiler 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 yesterday.

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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for coding agents

The implementation source of truth is docs/spec/WCC_AGENT_IMPLEMENTATION_SPEC_v0.2.1.md. Read it before changing anything. This file summarizes Section 0 of that document; where the two disagree, the specification wins.

Implement WCC in the phase order of specification Section 13. Do not broaden the scope without an explicit instruction from the project owner.

Rules

  1. Complete one phase and its acceptance criteria before starting the next phase.
  2. Prefer deterministic parsing over LLM inference whenever the same result can be obtained from HTML, ARIA, JSON-LD, or browser state.
  3. Do not implement irreversible actions such as purchase confirmation, account deletion, message sending, or state-changing form submission in MVP v0.1.
  4. Never execute a capability whose risk level is above low. Higher levels may be listed but must be blocked.
  5. Preserve evidence for every generated entity and capability. The system must be able to explain which DOM element or page signal produced each result.
  6. Add or update tests with every implementation change.
  7. Do not silently change schemas. Schema changes require a version increment and migration notes.
  8. Do not add an independent autonomous agent. WCC is a compilation and execution layer used by external agents.
  9. Keep the LLM provider optional and replaceable. Core extraction and execution must run without an LLM.
  10. All browser access goes through the Driver interface. Do not call Playwright APIs outside src/wcc/driver/.
  11. At the end of each phase, update docs/progress.md with completed work, test results, unresolved issues, and the next phase.
  12. Do not collapse CapabilityTemplate and BoundCapability into one model. Templates are portable and reusable; bound capabilities are session-scoped.
  13. Do not treat a structural hash as a reusable page signature. Implement the three fingerprints of specification 7.3 with their specified roles.
  14. Do not add dynamic MCP tool registration in MVP v0.1. Use the six stable tools of specification Section 12.

Read the full file on GitHub · 51 lines

Changes

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.

  1. yesterday First seen · 51 lines · 546 tokens per session scan A 2347ad14cac7

Subscribe to this mod's changes

web-capability-compiler AGENTS.md is an instructions file published in the GitHub repository Maaa2005/web-capability-compiler (0 stars, last pushed 21d ago), licensed MIT. It adds 546 tokens to every session, about $0.0027 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.