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/deepklarity/harness-kit/agents-mdgit clone --depth 1 https://github.com/deepklarity/harness-kitWhat 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 | $0.00383 | $0.00383 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
harness-kit 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.
What it actually says
AGENTS.md
You are a coding agent in the harness-kit repo. Start here.
What this repo is
A toolkit for humans and AI building software together: an orchestration CLI
(odin/), a task board (taskit/ — Django API + React UI), a provider quota
checker (harness_usage_status/), and portable engineering patterns
(.claude/skills/, docs/patterns/).
If you were sent here to adopt the patterns into another repo
Read docs/Quickstart.md and follow it exactly. It is
written for you.
If you are working on this repo
- Read
CLAUDE.md— the full operating manual (memory policy, git safety, testing discipline, subagent strategy). It applies to every agent, not just Claude. - Read
odin/docs/philosophy.md— the 20 tenets every change is judged against. - Each project has its own
CLAUDE.md/README.mdwith commands and conventions.
Commands you'll need
./dev.sh # start backend :9100, dashboard :9200, workers
source .venv/bin/activate && odin doctor # check providers
scripts/verify.sh # the one gate: all test suites, non-zero on any red
Hard rules
- Never run
git stashin the main checkout (parallel agents share it). - Never edit files inside
.odin/worktrees/. - Tests pass ≠ done — verify the change live, then show the evidence.
- Write like you talk:
docs/fable_roadmap/TONE.md.
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.
- 2d ago First seen · 41 lines · 383 tokens per session scan A 44d588e10fc3
harness-kit AGENTS.md is an instructions file published in the GitHub repository deepklarity/harness-kit (95 stars, last pushed 1mo ago), licensed MIT. It adds 383 tokens to every session, about $0.0019 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 2026-08-30.
Other instructions, from other repositories
nexent AGENTS.md
AGENTS.md instructions for ModelEngine-Group/nexent, covering agents, available skills, project overview, developer commands and backend (python 3.11).
neuron-ai AGENTS.md
AGENTS.md instructions for neuron-core/neuron-ai, covering neuron ai - project overview, the mental model: neuron is a composable workflow, development commands, architecture and modules.
neuron-ai CLAUDE.md
Claude Code instructions for neuron-core/neuron-ai, covering project overview, code standards, think before coding, simplicity first and surgical changes.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
memv CLAUDE.md
Instructions for vstorm-co/memv, covering claude.md, project overview, development setup, commands and quality.
Framework_Development_Guide
Instructions for rezaho/MARSYS, covering 0. golden principle, 1. layered architecture (mental model), 2. core classes & responsibilities, 2.1 module overview & logical flow and src/agents/ - agent architecture & communication.