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/ozgurcd/gograph/agents-mdgit clone --depth 1 https://github.com/ozgurcd/gographWhat 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 | $0.00439 | $0.00439 |
| Opus 5 | $0.00219 | $0.00219 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
gograph 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 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project authority
Current source, tests, generated CLI/MCP contracts, release artifacts, and live
services are the source of truth for behavior. llm-wiki/ stores durable
decisions, rationale, security constraints, provenance, and cross-session
context; it is not a substitute for verifying the code or current external
state. Generated gograph wiki pages are caches and must be freshness-checked
before use.
Conditional Scrinium use
Do not start Scrinium, call capabilities, or create a Scrinium session for a
read-only question, repository status check, trivial edit, or ordinary change
that creates no durable cross-session knowledge. A code or documentation change
by itself does not require a Scrinium session.
Use Scrinium when the task will create or update maintained llm-wiki/
content, or when a material architecture, security, release, governance, or
externally sourced decision should persist for future agents.
When Scrinium is required:
- Start one server for the working session with
scrinium ./scrinium.json. - Call
capabilitiesonce for that server connection, then callbegin_session. - Read
index.mdandagent-rules.md, which Scrinium requires before wiki writes. Read only the additional pages directly relevant to the task; do not preload the whole wiki. - Make project changes and write only durable knowledge through Scrinium. Do not log routine implementation details, formatting cleanup, or facts that are already obvious from source control.
- Update
log.md,index.md, andsource-registry.mdonly whensession_statusrequires them. Use one concise log entry per material outcome. - Call
session_statusandfinish_sessionbefore reporting completion of a session that was started. Do not call them when no Scrinium session exists.
Protected pages must use Scrinium's draft workflow. Scrinium governs writes made through its tools; it is workflow assistance, not a security boundary for arbitrary filesystem edits.
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 · 43 lines · 439 tokens per session scan A 34d3646def36
gograph AGENTS.md is an instructions file published in the GitHub repository ozgurcd/gograph (212 stars, last pushed 6d ago), licensed MIT. It adds 439 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 2026-08-30.
Other instructions, from other repositories
GoSQLX CLAUDE.md
Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
coldstart CLAUDE.md
Instructions for AkashGoenka/coldstart: Lightweight navigation layer for AI agents. Answers one question: which files are relevant to this task? Fast static index over file paths, symbol names, and exports — queried via two operations, find (ranked file paths matched against declared names: filenames, path segments…
gosymdb CLAUDE.md
Instructions for walkindude/gosymdb, covering working on gosymdb, what gosymdb does for navigation, session-start bootstrap, navigation tasks and the corresponding command and resolving fqnames.
dingo CLAUDE.md
Claude Code instructions for MadAppGang/dingo, covering claude ai agent instructions - dingo project, 🚨🚨🚨 stop: read this before any implementation 🚨🚨🚨, the architectural principle (understand this first), why this rule exists and ✅ required approaches (the only correct ways).
gosymdb AGENTS.md
Instructions for walkindude/gosymdb, covering agents.md — gosymdb, what gosymdb is, how the database is found, the freshness loop and mcp integration.