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/flohoss/gocron/agents-mdgit clone --depth 1 https://github.com/flohoss/gocronWhat 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 | $0.00761 | $0.00761 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
gocron 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidance
Read before making changes. Rule-oriented and self-contained.
Principles
- CLEAN code. Small functions, single responsibility, descriptive names, no dead code, no overengineering.
- No comments. Use descriptive function or service names instead.
- No code markers like
// ... existing code ...in edits. - Go imports: stdlib, then external, then internal (
github.com/flohoss/gocron/...), each block alphabetical. - Never edit generated files (
services/jobs/*.sql.go,models.go,web/src/client/).
Tooling — always via Docker Compose, never on the host
- Code generation:
docker compose run --rm backend sqlc generate - Backend format:
docker compose run --rm go fmt ./... - Format (all non-Go files):
docker compose run --rm format - Tests:
docker compose run --rm go test ./services/ ./config/ ./internal/... - E2E tests:
docker compose -f compose.yml -f compose.e2e.yml --profile test run --rm e2ethen... down - Rebuild & reload:
docker compose up
Only commit if format and tests pass.
Common Commands
docker compose run --rm npm install
docker compose run --rm --entrypoint npx npm --yes npm-check-updates -u && docker compose run --rm npm install
docker compose run --rm npm-e2e install
docker compose run --rm --entrypoint npx npm-e2e --yes npm-check-updates -u && docker compose run --rm npm-e2e install
docker compose run --rm go get -u ./...
docker compose run --rm go mod tidy
docker compose run --rm go fmt ./...
Compose pinned versions
compose.yml pins tool versions (V_GOLANG, V_AIR, V_SQLC, V_NODE, V_CYPRESS, V_DEBIAN). Check for new versions when updating deps:
V_GOLANG—go.dev/dl/?mode=jsonV_AIR—go list -m -versions github.com/air-verse/airV_SQLC—go list -m -versions github.com/sqlc-dev/sqlcV_NODE—nodejs.org/en/about/previous-releasesV_CYPRESS—hub.docker.com/r/cypress/included/tagsV_DEBIAN— Debian stable codename
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 · 64 lines · 761 tokens per session scan A 3ff6d671dfa8
gocron AGENTS.md is an instructions file published in the GitHub repository flohoss/gocron (549 stars, last pushed 5d ago), licensed MIT. It adds 761 tokens to every session, about $0.0038 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
duplicacy-mcp CLAUDE.md
Claude Code instructions for GeiserX/duplicacy-mcp, covering claude.md — duplicacy-mcp, tech stack, development, run tests and architecture.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, mandatory development principles and sow system.
IoTSharp AGENTS.md
Instructions for IoTSharp/IoTSharp, covering agents.md, current mission, current priority order, current concept realignment and ai workbench direction.
homebutler CLAUDE.md
Instructions for Higangssh/homebutler, covering homebutler, verify before claiming anything works, writing commits, prs, and comments, no tool attribution and commit subjects.
mcp-ssh-manager CLAUDE.md
Instructions for bvisible/mcp-ssh-manager, covering claude.md, project overview, architecture, commands and setup and installation.