What is secretsminter AGENTS.md?

Project instructions for secretsminter, a service that creates, places, and rotates cloud credentials without showing secret values to the requesting agent. They explain its security rules, code layout, testing, and logging conventions.

Onboarding an agent or developer before changing, testing, or operating the secretsminter repository.

They help contributors preserve the rule that secrets must not appear in tool responses or logs, and that credentials may only be placed in approved destinations.

secretsminter AGENTS.md — Instructions file by scorellis

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/scorellis/secretsminter/agents-md

Clone the repo

git clone --depth 1 https://github.com/scorellis/secretsminter

Made for: Codex, OpenCode.

Per session 1,169 This file is loaded in full into every session.

When invoked 1,169 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.

Model	Per session	Once invoked
Fable 5	$0.01169	$0.01169
Opus 5	$0.00584	$0.00584
Sonnet 5	$0.00234	$0.00234
Haiku 4.5	$0.00117	$0.00117

Measured yesterday against content hash 7b9d4f39848f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secretsminter 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — onboarding for anyone (human or AI) working in this repo

This is the tool-agnostic onboarding file. Read it before touching code, running the server, or consuming the repo. It captures the operational conventions that aren't obvious from the code alone.

What secretsminter is

A value-blind secrets-minter exposed to AI agents over MCP: it mints, places, and rotates cloud credentials without ever returning a secret value to the calling agent. Read README.md for the pitch and SECURITY.md for the threat model. The two invariants that govern everything:

Value-blind — no secret value crosses the tool boundary, an error string, or a log line.
Destination allow-list — a placement is refused unless it matches the signed manifest. This, not value-blindness, is the real trust root.

If a change you make could violate either, stop and re-read CONTRIBUTING.md.

Layout

packages/core (@secretsminter/core) — the key-holding internal tier: all security invariants, the broker pipeline, sinks. Everything network-free here is unit-tested.
packages/mcp (@secretsminter/mcp) — the agent-facing MCP server; holds no master keys.
packages/providers — Cloudflare/GitHub/Supabase plugins (all have real network paths; live-run status varies per story — Cloudflare live-verified, GitHub/Supabase unit-tested against fakes).
docs/adrs, docs/spikes, docs/stories — decisions, capability findings, and honest per-feature status.

Build & test

npm install
npm run build          # tsc --build, strict
npm test               # vitest
npm run test:coverage  # vitest + the coverage gate (90/85/88/90 on real logic)

The coverage gate runs locally (npm run test:coverage), not in CI — see the isolation principle.

Isolation — secretsminter is self-contained, stores nothing, manages other repos

secretsminter deploys as pure, isolated code someone stands up to run their own broker. Non-negotiable:

Read the full file on GitHub · 87 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.

yesterday First seen · 87 lines · 1,169 tokens per session scan A 7b9d4f39848f

Subscribe to this mod's changes

secretsminter AGENTS.md is an instructions file published in the GitHub repository scorellis/secretsminter (0 stars, last pushed 24d ago), licensed Apache-2.0. It adds 1,169 tokens to every session, about $0.0058 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.

Security Testing

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

secretsminter AGENTS.md