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/spasm-network/spasm-forum-server/agents-mdgit clone --depth 1 https://github.com/spasm-network/spasm-forum-serverWhat 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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
spasm-forum-server 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.
What it actually says
AI Agent Instructions
- Stack: Node.js/TypeScript with Express; async handlers; responses wrapped in
setTimeout(~200–300 ms). - API:
- Human-readable docs at
docs/api.md; typed interfaces intypes/interface.ts. - Use
format=spasm(JSON) unless RSS is required. Submit events as aSpasmEventEnvelopeV2object.
- Human-readable docs at
- Database: PostgreSQL.
- Tables:
spasm_events(signed and unsigned events wrapped in SpasmEventDatabaseV2). - Deprecated tables (you can optionally create them, but don't use them) are
posts,actions,actions_count. Initialize viadatabase.sqlornpm run initialize-db/npm run migrate.
- Tables:
- Setup:
- Create DB user and databases (
spasm_database,spasm_database_test); add credentials to.env. - Install:
nvm install 20 && nvm use 20 && npm ci.
- Create DB user and databases (
- Run:
- Dev:
npm run dev(test atlocalhost:5000/api/events). - Prod:
npm run prod(uses pm2;pm2 startup && pm2 savefor persistence).
- Dev:
- Admin panel: Configurable via spasm-forum-web at
/admin. Enable withENABLE_APP_CONFIG_CHANGES=true,ENABLE_ADMIN=true, and add admin pubkeys toADMINS=in.env. - Conventions:
- Use the interfaces from
types/interface.tsfor request/response shapes. - Prefer
format=spasm(JSON) unless RSS is explicitly required. - When submitting events, send a
SpasmEventEnvelopeV2object in the request body. - When signing events, add your pubkey as lower case.
- Use the interfaces from
- Troubleshooting: If DB permissions denied, grant usage/tables/sequences to the DB user.
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 · 23 lines · 417 tokens per session scan A 1ca1dd584e97
spasm-forum-server AGENTS.md is an instructions file published in the GitHub repository spasm-network/spasm-forum-server (10 stars, last pushed 2mo ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 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
expense-budget-tracker AGENTS.md
Instructions for kirill-markin/expense-budget-tracker, covering expense-budget-tracker, rules, components, supported clients and key paths.
postgres-skills AGENTS.md
Instructions for neondatabase/postgres-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.
pg_exporter AGENTS.md
Instructions for nbari/pg_exporter, covering agents.md, project shape, first steps, devpod workflow (preferred) and local commands.
ai-dba-workbench CLAUDE.md
Claude Code instructions for pgEdge/ai-dba-workbench, covering claude standing instructions, primary agent role, trivial-edit carve-out, project structure and key files.
mcp-database CLAUDE.md
Claude Code instructions for DiegoBulhoes/mcp-database, covering claude.md, commands, architecture, invariants (do not weaken) and adding or changing a tool.
pgbent copilot-instructions.md
Copilot instructions for gregs1104/pgbent: This file exists for GitHub Copilot compatibility. The canonical agent guide is AGENTS.md at the repository root.