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/sovantica/engrava/copilot-instructionsgit clone --depth 1 https://github.com/sovantica/engravaWhat 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 | $0.00444 | $0.00444 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
engrava 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 3d 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
Copilot Instructions — engrava
Public repository (engrava) — Graph memory database for AI agents.
License: MIT. Primary language: python 3.11+.
Commit messages
- Use Conventional Commits 1.0.0:
<type>(<scope>): <description>. SeeCLAUDE.mdfor the type table. - Use only durable public identifiers: this repo's release tags (
vX.Y.Z), this repo's GitHub issue/PR numbers (#N). - Generic feature descriptions are welcome; concise imperative subject lines preferred (max 72 chars).
- Default PR target:
dev.
Branch names
- Format:
<type>/<kebab-description>. Plain English. ≤ 50 chars. - No internal identifiers, no abbreviations that wouldn't make sense to someone reading the repo for the first time.
Code style
- Follow the existing patterns in
src/. Read 3-5 nearby files before introducing a new pattern. - Adhere to the quality bar described in
CLAUDE.md— linting clean, typing strict, coverage above threshold, no shortcuts. - Match the project's existing naming, file layout, and import conventions; don't invent new structures unprompted.
What to avoid
- Don't reference internal-looking identifiers or paths in commits, code comments, or PR descriptions. If something feels like it belongs to a private workflow, leave it out and the maintainer can add a public mapping (a
#Nissue/PR reference) later. - Don't introduce dependencies without checking the project's existing stack — extra deps need explicit justification.
- Don't suggest
--no-verifyto skip the local pre-commit hook except in maintainer-approved emergencies.
When you're unsure
Default to omitting the uncertain reference. Ask the maintainer in a PR comment or a draft message. The local pre-commit hook gives you a fast feedback loop on commit-message hygiene; pay attention to its output.
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.
- 3d ago First seen · 35 lines · 444 tokens per session scan A e997d50c38c5
engrava copilot-instructions.md is an instructions file published in the GitHub repository sovantica/engrava (5 stars, last pushed 9d ago), licensed MIT. It adds 444 tokens to every session, about $0.0022 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
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
AIPass CLAUDE.md
Instructions for AIOSAI/AIPass, covering aipass, startup protocol and memories.
AIPass AGENTS.md
Instructions for AIOSAI/AIPass, covering aipass, startup protocol and memories.
vellis AGENTS.md
Instructions for volantlabs/vellis, covering agents.md, repository purpose, startup checks, installing vellis for a user and model-first component workflow.
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.
COORD-Harness AGENTS.md
AGENTS.md instructions for 0marm0/COORD-Harness, covering coordharness agent entrypoint, start and finish and context hierarchy.