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/fetchai/innovation-lab-examples/testgit clone --depth 1 https://github.com/fetchai/innovation-lab-examplesWhat 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 | $0.00226 | $0.00226 |
| Opus 5 | $0.00113 | $0.00113 |
| Sonnet 5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
innovation-lab-examples test.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Writing Tests for Canister Functions
When writing tests for canister functions:
- Use Jest for canister testing
- Include setup, execution, and assertion phases in each test
- Test both happy path and error cases
- Use descriptive test names that explain the expected behavior
Example test structure:
it("should [expected consequence]", async () => {
// Setup
const testData = "world";
// Execute
const response = await fetch(`${origin}/db/update`, {
method: "POST",
headers: [["Content-Type", "application/json"]],
body: JSON.stringify({
hello: testData,
}),
});
const responseJson = await response.json();
// Assert
expect(responseJson).toEqual({ hello: "world" });
});
After writing the tests, check if the file has any errors:
npx tsc -p ic/tsconfig.json
Then check that they are all passing by executing:
npm test
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.
- 2d ago First seen · 48 lines · 226 tokens per session scan A 76da16a5482e
innovation-lab-examples test.instructions.md is an instructions file published in the GitHub repository fetchai/innovation-lab-examples (1,148 stars, last pushed 19d ago), licensed MIT. It adds 226 tokens to every session, about $0.0011 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
ii-agent CLAUDE.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent project guide, project overview, architecture, domain structure and orm base & id conventions.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
a2a-editor CLAUDE.md
Instructions for open-resource-discovery/a2a-editor, covering claude.md, project overview, commands, development and building.
agentic-sandbox CLAUDE.md
Claude Code instructions for jmagly/agentic-sandbox, covering claude.md, repository purpose, tech stack, development commands and management server.
agentspore AGENTS.md
AGENTS.md instructions for AgentSpore/agentspore, covering agentspore — internal agents, shared infrastructure, modelpool (modelpool.py), platformclient (platformclient.py) and vcsclient (vcsclient.py).
agentspore CLAUDE.md
Claude Code instructions for AgentSpore/agentspore, covering agentspore — claude instructions, github release notes, работа с субагентами (обязательно), knowledge graph (graphify) and when to query the graph.