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.
npx agentmods add instructions/farchanjo/merkle/agents-mdgit clone --depth 1 https://github.com/farchanjo/merkleWrote 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/farchanjo/merkle/agents-md)<a href="https://agentmods.dev/instructions/farchanjo/merkle/agents-md"><img src="https://agentmods.dev/badge/instructions/farchanjo/merkle/agents-md.svg" alt="Measured on agentmods" 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 | $0.01012 | $0.01012 |
| Opus 5 | $0.00506 | $0.00506 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
merkle 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-vault — Agent Context
Canonical map for AI agents. Dense, factual, path-anchored.
Project
Merkle local-first MCP vault. Architecture: docs/arch. Speckit plane: doc/arch (with symlinks to docs/arch). Dual-tree is intentional.
Spec-first protocol
spec-first: read docs/arch and doc/arch before code. Never hand-edit doc/.specify databases. Use the installed speckit binary.
Architecture
Hexagonal: merkle-types, domain crates, merkle-ports, adapters (merkle-adapter-companion-socket, merkle-adapter-crypto, merkle-adapter-external-services, merkle-adapter-keychain, merkle-adapter-mcp, merkle-adapter-oob, merkle-adapter-sqlite), merkle-application, merkle-companion-client, merkle-companion-contract, merkle-bdd, merkle-e2e, merkle-domain-access-mediation, merkle-domain-audit-compliance, merkle-domain-backup-recovery, merkle-domain-identity, merkle-domain-policy-permissions, merkle-domain-secret-storage.
Commands
speckit analyze
speckit ask
speckit brief
speckit check
speckit clarify
speckit commit check
speckit commit suggest
speckit completions
speckit config drift
speckit config get
speckit config list
speckit config set
speckit config unset
speckit constitution
speckit context pack
speckit context score
speckit dedupe
speckit diagram render
speckit dismiss
speckit explain
speckit feature archive
speckit feature compact
speckit feature insert
speckit feature list
speckit feature new
speckit feature renumber
speckit feature reorder
speckit feature restore
speckit feature select
speckit gitlab status
speckit gitlab sync
speckit guard check
speckit guard hook
speckit guide
speckit hook post-edit
speckit hook pre-commit
speckit hook session-start
speckit hook user-prompt
speckit implement
speckit init
speckit library add
speckit library ask
speckit library browse
speckit library export
speckit library extract
speckit library import
speckit library list
speckit library open
speckit library remove
speckit library search
speckit library serve
speckit library show
speckit library update
speckit library validate
speckit license check
speckit license list
speckit license set
speckit license show
speckit manual
speckit mermaid render
speckit migrate
speckit missing
speckit model add
speckit model api apply
speckit model api list
speckit model api select
speckit model check
speckit model fetch
speckit model list
speckit model remove
speckit model select
speckit next
speckit off
speckit on
speckit pack add
speckit pack export
speckit pack import
speckit pack list
speckit pack remove
speckit pack update
speckit plan
speckit plan setup
speckit reindex
speckit search
speckit semantic deep-status
speckit semantic enable
speckit semantic eval
speckit semantic off
speckit semantic status
speckit spec score
speckit specify
speckit stats attributes
speckit stats compliance
speckit stats corpus
speckit stats findings
speckit stats guard
speckit stats profile
speckit stats recommendations
speckit status
speckit tasks
speckit tasks setup
speckit validate
speckit verify
speckit version
speckit workflow render
make check
make test
make lint
make doctor
make doctor-full
make deploy
make build
make build-release
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.
- 5d ago First seen · 155 lines · 1,012 tokens per session scan A a547b520e23a
merkle AGENTS.md is an instructions file published in the GitHub repository farchanjo/merkle (2 stars, last pushed 26d ago), licensed Apache-2.0. It adds 1,012 tokens to every session, about $0.0051 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.
Other instructions, from other repositories
fastify-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/fastify-boilerplate, covering agents.md, project overview, quick reference, architecture and layer boundaries (critical).
event-store-adapter-js AGENTS.md
AGENTS.md instructions for j5ik2o/event-store-adapter-js, covering agents.md, 言語, github pull request のモニタリング, $grill-me 実行時の作業判断 and 軽い作業の場合.
blueclaw AGENTS.md
AGENTS.md instructions for yeomyeonggeori/blueclaw, covering agents.md, core principles, single source of truth, working on this repository and branch names.
violet AGENTS.md
AGENTS.md instructions for VOD-Studio/violet, covering violet (blog-project), 架构与代码边界, 架构耦合约束, 开发流与命令 (makefile) and 后端 (api/) 须知.
obsigna go.instructions.md
Instructions for agent-receipts/obsigna, a project described as: Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.
obsigna python.instructions.md
Instructions for agent-receipts/obsigna, a project described as: Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.