Borrowing it
Nothing to install: this file belongs to BlackbirdWorks/gopherstack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BlackbirdWorks/gopherstack/main/AGENTS.mdgit clone --depth 1 https://github.com/BlackbirdWorks/gopherstackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/blackbirdworks/gopherstack/agents-md)<a href="https://agentmods.dev/instructions/blackbirdworks/gopherstack/agents-md"><img src="https://agentmods.dev/badge/instructions/blackbirdworks/gopherstack/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/blackbirdworks/gopherstack/agents-md"><img src="https://agentmods.dev/badge/instructions/blackbirdworks/gopherstack/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.02152 | $0.02152 |
| Opus 5.5 | $0.00861 | $0.00861 |
| Sonnet 5.5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
gopherstack 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 yesterday.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
You are an expert Go and TypeScript engineer. You write idiomatic Go: small focused functions (under 100 lines), cyclomatic complexity below 15 (extract helpers — never use //nolint), named constants instead of magic strings, explicit error handling, no goroutine or resource leaks. You know the AWS SDK v2 deeply and build accurate AWS service simulations.
Pre-push checklist — ALL must pass before every commit:
goimports -w -local github.com/blackbirdworks/gopherstack ./services/<pkg>/...
golines -w --max-len=120 ./services/<pkg>/...
go test ./services/<pkg>/... -short -count=1
go vet ./services/<pkg>/...
golangci-lint run ./services/<pkg>/...
task lint also runs mulint (mutex misuse detection) via go vet -vettool.
mulint cannot follow mutex wrappers across package boundaries, so it does
not see lockmetrics.RWMutex (used almost everywhere in this repo) — it
only guards direct sync.Mutex/sync.RWMutex use.
Logging — context-aware only (no exceptions):
- NEVER call
slog.Default()or construct an ad-hocslog.New(...)in service/production code, and NEVER embed or store a*slog.Loggeron a struct/global. The single allowedslog.Default()is the fallback insidepkgs/logger.Load; the single allowedslog.Newispkgs/logger.NewLogger. - Always fetch the logger from context:
logger.Load(ctx), and prefer the*Contextmethods (InfoContext/WarnContext/...) so the request/worker fields propagate. - The root logger is created once at startup and injected into
ctx. Enrich it, never replace it:logger.WithService(ctx, name)at a service boundary (done centrally per request),logger.AddAttrs(ctx, ...)for extra fields, andlogger.WithWorker(ctx, service, job)at the entry of every background routine (records log asworker=<service>-<job>). - Background routines (janitors, debounced saves, accept loops) MUST derive their logger
from the lifecycle/root context (e.g. the janitor context), NEVER from a per-request
echocontext — otherwise they leakrequest_idand pin a finished request alive. - The logger is a pointer carried in
ctx; enrichment is copy-on-write (slog.Logger.Withreturns a new logger). Do NOT mutate it, do NOT callslog.SetDefaultat runtime, and do NOT callWithService/WithWorker/AddAttrsinside a loop (each call layers attributes — derive once at entry; for per-item fields use a locall := logger.Load(ctx).With(...)). - Do NOT introduce
context.Background()/context.TODO()in service code or tests to satisfy a signature — thread the real request/root context (in tests uset.Context()).
Checkpoint commits for long tasks: For tasks taking >1 hour, commit and push every ~30 minutes:
git add -A && git commit -m "WIP: checkpoint" && git push origin HEAD
Subagent Isolation: When dispatching subagents for concurrent tasks, always isolate working trees (Workspace: 'branch' or git worktree) to avoid cross-contamination of uncommitted edits, task docs regeneration, or intermediate build artifacts.
This project uses bd (beads) for issue tracking. Run bd prime for full workflow context.
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.
- yesterday First seen · 169 lines · 2,152 tokens per session scan A 7877ee3183e4
gopherstack AGENTS.md is an instructions file published in the GitHub repository BlackbirdWorks/gopherstack (17 stars, last pushed yesterday), licensed MIT. It adds 2,152 tokens to every session, about $0.0086 per session on Opus 5.5. 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 2026-11-07.
gopherstack AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gopherstack AGENTS.mdBlackbirdWorks/gopherstack | Instructions file | 17 | yesterday | MIT | A | 2,152 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |