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/stepanov1975/hermes-local-knowledge/agents-mdgit clone --depth 1 https://github.com/stepanov1975/hermes-local-knowledgeWrote 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/stepanov1975/hermes-local-knowledge/agents-md)<a href="https://agentmods.dev/instructions/stepanov1975/hermes-local-knowledge/agents-md"><img src="https://agentmods.dev/badge/instructions/stepanov1975/hermes-local-knowledge/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 5.1 | $0.01586 | $0.01586 |
| Opus 5 | $0.00793 | $0.00793 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
hermes-local-knowledge 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for hermes-local-knowledge
These instructions apply to the whole repository.
Before editing
- Read
README.md,CONTRIBUTING.md, andmemory.md. - Check
git status --short --branch; preserve unrelated dirty work. - Keep changes focused. Runtime dependencies remain Python standard library only unless a documented product need justifies otherwise.
- Never commit generated/local state or secrets.
Documented public boundaries
- Package version is synchronized in
plugin.yaml,pyproject.toml, andhermes_local_knowledge/__init__.py. - The Python plugin entry point is
local_knowledge = hermes_local_knowledge.plugin;plugin.registeris the registration boundary. - Registration provides exactly five native tools (
knowledge_search,knowledge_get,knowledge_neighbors,knowledge_feedback,knowledge_usage_report) and four hooks (pre_llm_call,post_tool_call,on_session_end,on_session_finalize). indexer.__all__is exactly:Artifact,Edge,IndexSettings,build_index,search_index,get_artifact,get_neighbors,main.python -m hermes_local_knowledge.cliis the primary standalone CLI.python -m hermes_local_knowledge.indexeris the preserved compatibility entry point.hermes local-knowledgeis the smaller install/doctor surface; its worker command is host-internal.- Preserve documented configuration aliases and defaults. Do not preserve undocumented private call shapes merely because a test once patched them.
- The three router-skill copies are an intentional packaging/install exception to DRY and must remain byte-identical with one equality assertion in
tests/test_public_contract.py.
Current owners
config.py: configuration models and resolution.implicit.py: default-enabled search-result consumption feedback.artifacts.py: whole-artifact models, collection, privacy-safe metadata, graph edges.index.py: format-4 persistence, cross-version/SQLite build locks, rebuild classification, deterministic retrieval.telemetry.py: usage/feedback persistence and reports.routing.py: bounded explicit and implicit feedback-assisted routing.evaluation.py: read-only feedback replay and metrics.service.py: managed index and telemetry lifecycle for one resolved config.okf.py: safe OKF queue, hooks, worker, validation, fenced publication.plugin.py: Hermes tools/hooks/skill/CLI registration.cli.py: standalone and Hermes CLI adapters.indexer.py: thin compatibility facade.__init__.py: package version.
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 Changed · -13 tokens per session 4d6d2d3f6da4
- 6d ago First seen · 97 lines · 1,599 tokens per session scan A 4e65bd32df86
hermes-local-knowledge AGENTS.md is an instructions file published in the GitHub repository stepanov1975/hermes-local-knowledge (8 stars, last pushed 5d ago), licensed MIT. It adds 1,586 tokens to every session, about $0.0079 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
Noshy AGENTS.md
Instructions for Noshkoto/Noshy, covering noshy — ai agent instructions, what noshy is, architecture principles, how to work on this codebase and what not to do.
company-brain-starter AGENTS.md
Instructions for Toni-Agent/company-brain-starter, covering agents.md — company brain operating template, intended reader, unconfigured starter gate, mission and source-of-truth order.
hermes-esra AGENTS.md
Instructions for rrpauls/hermes-esra, covering agents.md — esra integration for hermes, core rule, install layout (where things live), how to run the orchestrator and recommended triggers.
h5i-ctx2img AGENTS.md
Instructions for Koukyosyumei/h5i-ctx2img, covering persona, h5i integration, workflow, code commits and capturing large command output (token reduction).
loom-kg AGENTS.md
Instructions for gl00mt1t4n/loom-kg, covering agents, first response rule, setup questions, agent runtime compatibility and after the user answers.
github-claw AGENTS.md
AGENTS.md instructions for liyupi/github-claw, covering agents.md — ai 助手核心定义, 1. 我是谁, 2. 我如何在这个仓库中工作, 文件即记忆 and 工作原则.