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/spica-engine/spica/performance-optimizationgit clone --depth 1 https://github.com/spica-engine/spicaWhat 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 | $0.04642 | $0.04642 |
| Opus 5 | $0.02321 | $0.02321 |
| Sonnet 5 | $0.00928 | $0.00928 |
| Haiku 4.5 | $0.00464 | $0.00464 |
Grade C, and why
spica performance-optimization.instructions.md scanned grade C with 1 finding 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- End of Performance Optimization Instructions --> The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- today First seen · 421 lines · 4,642 tokens per session scan C 2f742336cb67
spica performance-optimization.instructions.md is an instructions file published in the GitHub repository spica-engine/spica (100 stars, last pushed 7d ago), licensed AGPL-3.0. It adds 4,642 tokens to every session, about $0.0232 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other instructions, from other repositories
js-bson AGENTS.md
Instructions for mongodb/js-bson, covering agents.md, project overview, commands, benchmarks and structure.
KarmaCircle AGENTS.md
Instructions for karmacircleCommunity/KarmaCircle, covering agentic workflow, git / branching, the apps/web ↔ apps/api boundary, repo-specific guardrails and when you're not sure which duplicate a request means.
kerberos AGENTS.md
Instructions for mongodb-js/kerberos, covering agents.md, project overview, commands, structure and code conventions.
KarmaCircle CLAUDE.md
Instructions for karmacircleCommunity/KarmaCircle, covering monorepo layout, graphify — check the knowledge graph first, caveman — always run ultra mode in this repo, git workflow and responsive design — mandatory for every component.
zstd AGENTS.md
Instructions for mongodb-js/zstd, covering agents.md, project overview, commands, structure and code conventions.
js-bson CLAUDE.md
Instructions for mongodb/js-bson, a project described as: BSON Parser for node and browser.