AGENTS

A contributor-rules file for changes under app/agents/ in a repository with governed chat and delivery workflows.

In plain words
What is it for?
Use it before modifying the repository’s agent code, especially governance chat, document registry access, or related service boundaries.
Why use it?
It tells contributors which specifications to read and which architecture boundaries and state-changing operations to preserve.

Agent

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 agents/thanhtung2693/specgate/agents
Clone the repo
git clone --depth 1 https://github.com/thanhtung2693/specgate
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 734 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00734
Opus 5 $0.00000 $0.00367
Sonnet 5 $0.00000 $0.00147
Haiku 4.5 $0.00000 $0.00073

Measured 2d ago against content hash 0464c153c3fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS 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.

app/agents/AGENTS.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Operations Contributor Rules

Extends the root contributor rules. This file applies only to changes under app/agents/.

Read before changing behavior

Run the service with uv sync --all-groups and uv run langgraph dev; see README.md for the complete contributor flow.

Architecture boundaries

  • governance_chat.py:graph is the only graph declared in langgraph.json. It is a thin, read-only governance-chat surface over governed artifacts, readiness results, and Knowledge.
  • State-changing governance operations such as gate execution and delivery review are deterministic Python services exposed by webapp.py; do not route them through chat merely for convenience.
  • Repository implementation and artifact authoring stay in IDE/CLI workflows. Do not add open-ended repository tools, PRD/spec drafting, or transport overlays to governance chat.
  • Access Doc Registry through its documented REST API. Do not couple this module to Postgres, SQLite, S3, or Doc Registry internals.
  • Add a DocRegistryClient method only when production code calls it.
  • Design references are governed artifact metadata; this service does not inspect external design tools directly.

Natural-language control flow

SpecGate accepts English, Vietnamese, mixed-language input, abbreviations, and domain-specific phrasing. Do not route, classify, or extract meaning from user text with keyword lists, regexes, fixed phrases, punctuation, capitalization, length thresholds, or language detection.

Use LLM classification with structured output through llm_structured.py:structured_output_ainvoke. Structural program values such as event names, enum values, node IDs, environment names, and JSON keys may be matched directly.

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 0 tokens per session scan A 0464c153c3fa

Subscribe to this mod's changes

AGENTS is an agent published in the GitHub repository thanhtung2693/specgate (5 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 734 tokens. 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.