Borrowing it
Nothing to install: this file belongs to kyzdes/keys-keeper-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kyzdes/keys-keeper-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/kyzdes/keys-keeper-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kyzdes/keys-keeper-skill/agents-md)<a href="https://agentmods.dev/instructions/kyzdes/keys-keeper-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kyzdes/keys-keeper-skill/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kyzdes/keys-keeper-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kyzdes/keys-keeper-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00380 | $0.00380 |
| Opus 5.5 | $0.00152 | $0.00152 |
| Sonnet 5.5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
keys-keeper-skill 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 15d 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.
What it actually says
Keys Keeper development
Start with docs/architecture/VPS-REFACTOR-2026-10-02.md for current scope,
VPS contracts and validation. HARDENING-2026-10-02.md records the preceding
mutation/private-file hardening. Earlier reviews describe their pinned
baselines, not the current working tree.
- Keep CLI, HTTP and workers as adapters around application/domain code.
- S3/WebVault were removed. KK1 file backup, local admin, KK2 VPS and KK3
project/personal sync remain. Snapshot preparation lives in
vault_snapshot. - Never skip fresh remote membership/revocation or signed ancestry verification to optimize VPS history. Relay quota counters must share the data transaction.
- Ordinary master writes use
VaultServiceandMasterMutationManagerfor both metadata schemas. Do not add another exception-only rollback path. - Use
private_filesfor bounded private IO andrequest_jsonfor local JSON request contracts. Windows creation must set its DACL before writing data. - Agent instructions live in
src/keys_keeper/agent_rules/canonical.py. Regenerate shipped skills, references and rule fixtures after changing it. - Run tests against temporary synthetic vaults. Ordinary pytest isolates the clipboard; native clipboard tests require explicit environment opt-in. Never run diagnostics against the operator's vault or login keychain.
- Existing dependencies and ordinary HTML/JS are sufficient. Add no optional UI libraries or new storage/protocol mechanisms without a concrete need.
Local validation: PYTHONPATH=src .venv/bin/python -m pytest -q -o addopts=''.
The CI matrix also covers Windows native DACLs, Linux Secret Service, Python
3.10/3.14, native macOS builds and installed-wheel generation.
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.
- 15d ago First seen · 28 lines · 380 tokens per session scan A 008d3255eacf
keys-keeper-skill AGENTS.md is an instructions file published in the GitHub repository kyzdes/keys-keeper-skill (3 stars, last pushed 14d ago), licensed MIT. It adds 380 tokens to every session, about $0.0015 per session on Opus 5.5. 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 2026-10-03.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.