verchestra AGENTS.md

Repository-specific instructions for Verchestra, a tool for verified AI-assisted software delivery.

In plain words
What is it for?
Use them when working on Verchestra’s code, documentation, qualification process, or release decisions.
Why use it?
They give agents the project’s current release status, required starting checks, repository map, and rules for describing its qualification state accurately.

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/accd/verchestra/agents-md
Clone the repo
git clone --depth 1 https://github.com/accd/verchestra

Made for: Codex, OpenCode.

Per session 1,140 This file is loaded in full into every session.
When invoked 1,140 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 $0.01140 $0.01140
Opus 5 $0.00570 $0.00570
Sonnet 5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2d ago against content hash 8e2f89ef475e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verchestra 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.

AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verchestra Repository Instructions

Mission and current status

Verchestra is a verified AI software-delivery harness. It is currently 0.0.0-qualification: T77 is complete and the declared qualification chain is fully verified. That is not a release. The signed promote-or-reject decision the contract (docs/qualification/RELEASE-DECISION-CONTRACT.md) requires has been made: it is a signed reject — a recorded hold — (docs/qualification/release-decision-1.0.0.md, #18). The candidate is fit to keep operating as 0.0.0-qualification and is not promoted to 1.0.0; a promote round would decide on a fresh candidate with its own decision file, after the tracked promote-readiness work lands. The verchestra npm package is published at 0.0.0-qualification, so a public installer exists and may be described truthfully; do not claim production readiness or a 1.0 release.

These instructions are provider-neutral and sufficient after a clean clone. Git and tracked repository artifacts are authoritative; chat history, provider memory, IDE integrations, MCP servers, and installed skills are optional.

Start every task

  1. Run git status --short --branch and git rev-parse HEAD.
  2. Read the issue or request, this file, and the closest scoped AGENTS.md.
  3. Read docs/architecture.md, ROADMAP.md, and any active feature .specs/features/<slug>/handoff.md.
  4. Use corepack pnpm agent:context when available to confirm status, required reads, active work, and repository gates.
  5. Identify the canonical source before editing. Generated projections and build output are never canonical.

Closest scoped instructions refine these rules for their subtree. They must not contradict or relax this file.

Repository map

Read docs/repository-map.md before changing package boundaries. Inward dependency direction is contracts → domain → application; adapters may depend on those inward packages but not sibling adapters. apps/vestra-cli is the composition root. apps/site is a build-time documentation projection.

Read the full file on GitHub · 114 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 · 114 lines · 1,140 tokens per session scan A 8e2f89ef475e

Subscribe to this mod's changes

verchestra AGENTS.md is an instructions file published in the GitHub repository accd/verchestra (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,140 tokens to every session, about $0.0057 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.

Related

Other instructions, from other repositories

ai-engineering-skills AGENTS.md

Instructions for tmusser/ai-engineering-skills, covering agent instructions, route-first context loading and quality standards.

tmusser/ai-engineering-skills · 385 tokens

scrub-mcp AGENTS.md

AGENTS.md instructions for zombat/scrub-mcp, covering s.c.r.u.b. agent instructions, prime directive, prohibited actions (the bash ban), division of labor and context gathering rules (map-then-navigate).

zombat/scrub-mcp · 1,716 tokens

nextclaw AGENTS.md

Instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.

Peiiii/nextclaw · 3,095 tokens

medusa CLAUDE.md

Claude Code instructions for Pantheon-Security/medusa, covering medusa - medusa security scanning, critical: release gate — do not skip, 4. security hardening tests (must show: all pass), critical: bash sandbox and project overview.

Pantheon-Security/medusa · 2,806 tokens

slipway AGENTS.md

Instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.

signalridge/slipway · 470 tokens

nobrainer-tech-skills copilot-instructions.md

Instructions for nobrainer-tech/nobrainer-tech-skills: The fifteen canonical Agent Skills are under skills/; retired predecessors exist only in Git history. Read the relevant skills/ /SKILL.md before changing a skill.

nobrainer-tech/nobrainer-tech-skills · 359 tokens