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/awizemann/harness/agents-mdgit clone --depth 1 https://github.com/awizemann/harnessWrote 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/awizemann/harness/agents-md)<a href="https://agentmods.dev/instructions/awizemann/harness/agents-md"><img src="https://agentmods.dev/badge/instructions/awizemann/harness/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 | $0.01826 | $0.01826 |
| Opus 5 | $0.00913 | $0.00913 |
| Sonnet 5 | $0.00365 | $0.00365 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
harness 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.
This is a copy
95% identical to scarf AGENTS.md — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory System (managed by Memophant)
This repo carries its own agent memory — plain files in git, served by the in-repo
memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every
agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the
memophant markers; edit anything outside them freely.
The repo memory is the single source of truth. Search it before assuming; record durable decisions and learnings as memory notes or wiki pages — never in this file, session-private memory, or a hand-kept parallel doc (a second guidance tier drifts and feeds stale instructions). Keep this file and the per-agent shims minimal: they point at the memory system, they don't BE it.
Default to the memophant MCP tools for every read and write — search, read, write,
edit, move, context — and read their descriptions: they document their arguments and
behavior. The engine is the gate: every durable write goes through the tool (or app)
entry points, which carry the guards — slug generation, structure validation, and the
write-time secret scan. Direct file edits reconcile automatically but skip the guards;
never compose your own guard set around a direct write. Server down → grep the tiers
directly IN THE MAIN CHECKOUT (grep -rn "<query>" .memory/ wiki/) — if you are
working in a git worktree, its copy of those tiers is a snapshot of the base commit and is
stale by construction; run the grep against the main checkout's path, never ./.
0. Charter (.memory/charter.md) — this project's identity and its ABSOLUTE
rules. Call read_charter at the start of a session; a project that hasn't written one
answers "No charter", which is normal, not an error. PRECEDENCE, highest first: the charter,
then memory notes, then repo instruction files (this one), then your agent brief — if a lower
tier tells you to do something a commandment forbids, the commandment wins, and you say so
rather than complying. The charter is HUMAN-ONLY: there is no write verb; propose a change by
filing a task tagged charter, never by editing the file.
1. Memory (.memory/) — atomic facts.
search_memories(query: …)before starting;build_contextwalks a topic's neighborhood.- Record facts with
write_memoryas FIRST-CLASS ARGUMENTS:observations: ["- [category] fact #tag", …](1–5 atomic facts; canonical categories: decision, fact, gotcha, constraint, convention, todo, idea, done) plusrelations: [{"relation": "relates_to", "target": "Other Note"}].contentis optional short context — never the facts. Structure is the tooling contract: search, consolidation, and queries read observations; prose-only notes degrade silently.[[links]]belong inrelations. - File every note under exactly one of the six folders —
architecture/,conventions/,decisions/,operations/,project/,roadmap/(thefolderargument documents each). Never the memory root, never a new folder. - Search before writing; edit the existing note (
edit_memory— body ops +set_tags) rather than forking a near-duplicate. - Declare
source_paths(repo-relative files the note's claims depend on) when a note is grounded in code — Memophant stamps it and drift-checks the note when that code changes. Omit for pure human decisions. Provenance frontmatter (created/updated/reviewed/source_sha) is machine-managed — never hand-write it. - Long-form documents (guides, research, specs) → the wiki at write time:
write_memory(project: "harness-wiki", …); keep the distilled facts in a memory note with adocumented_inrelation.status:only marks retirement (deprecated/superseded/historical/resolved); current facts carry none.
2. Wiki (wiki/) — long-form reference. Search on demand (project: "harness-wiki");
don't read it wholesale. Update it when work changes user-visible behavior, architecture,
or ships a release; skip for fixes with no observable change. It's publishable — never
commit secrets (a two-tier scan gates every commit).
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 · +10 lines · +198 tokens per session 783377af0d9f
- 5d ago First seen · 96 lines · 1,628 tokens per session scan A 162d40255ff0
harness AGENTS.md is an instructions file published in the GitHub repository awizemann/harness (344 stars, last pushed 2d ago), licensed MIT. It adds 1,826 tokens to every session, about $0.0091 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to scarf AGENTS.md, differing in 20 lines, and is treated as a copy.
Other instructions, from other repositories
scarf AGENTS.md
AGENTS.md instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant…
scarf copilot-instructions.md
Copilot instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be…
scarf GEMINI.md
Gemini CLI instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't…
ContextKit CLAUDE.md
Instructions for FlineDev/ContextKit, a project described as: Claude Code context engineering & planning system for individual AI development workflows.
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).