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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/awizemann/harness/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/awizemann/harness/copilot-instructions.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 | $0.00571 | $0.00571 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
harness copilot-instructions.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
100% identical to scarf copilot-instructions.md — 3 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.
What it actually says
Memory System (managed by Memophant) — core rules. Full reference: AGENTS.md.
- Memory is the source of truth. Search it before assuming; record durable decisions/learnings as memory notes or wiki pages — never in this file or session-private/model memory. Search before writing and edit an existing note (
edit_memory) rather than forking a near-duplicate. - Prefer the
memophantMCP tools for every read/write (search/read/write/edit/move) — read each tool's description (they document their args). The engine is the gate: the tool/app entry points carry the guards (slug-gen, structure validation, write-time secret scan); direct edits reconcile automatically but skip them — never compose your own guard set. Tools absent → grep the MAIN CHECKOUT's.memory/+wiki/; a git worktree's copy of those tiers is a base-commit snapshot and is stale by construction, so never grep./from one. - Don't
git add/committhe managed tiers (.memory/,wiki/,design/,code/,sessions/,documents/,vendors/,templates/,TASKS.md,tasks/) — the user commits each via Memophant's per-tier secret-scanned bar; leave them dirty. Everything else is yours. - Secrets → Keychain, never chat or files. Found or made a credential? Store it with
set_vendor_credential(fetch later withget_vendor_credential); never leave it loose in chat. - Agent artifacts (plans/reports/briefs) →
documents/(exact lowercase), viawrite_tier_file(tier: "documents", path: …)— never a repo'sdocs/folder (that's the project's own documentation) and never a case-variant likeDocuments/. - Read the project charter (
read_charter) at session start when this project has one (.memory/charter.md) — its commandments are absolute and OUTRANK memory notes, this file, and your brief; "No charter" is a normal answer. It's human-only: propose changes as a task taggedcharter, never edit it. File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, passsource_paths(the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be kept current.
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 · +1 lines · +110 tokens per session f4e6c75d54f7
- 5d ago First seen · 11 lines · 461 tokens per session scan A ddf71ea4538e
harness copilot-instructions.md is an instructions file published in the GitHub repository awizemann/harness (344 stars, last pushed 2d ago), licensed MIT. It adds 571 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to scarf copilot-instructions.md, differing in 3 lines, and is treated as a copy.
Other instructions, from other repositories
scarf 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 markers…
scarf copilot-instructions.md
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 kept…
scarf GEMINI.md
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 kept…
ContextKit CLAUDE.md
Instructions for FlineDev/ContextKit, a project described as: Claude Code context engineering & planning system for individual AI development workflows.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
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).