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/mudrii/golink/claude-mdgit clone --depth 1 https://github.com/mudrii/golinkWrote 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/mudrii/golink/claude-md)<a href="https://agentmods.dev/instructions/mudrii/golink/claude-md"><img src="https://agentmods.dev/badge/instructions/mudrii/golink/claude-md.svg" alt="Measured on agentmods" 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 | $0.02874 | $0.02874 |
| Opus 5 | $0.01437 | $0.01437 |
| Sonnet 5 | $0.00575 | $0.00575 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
golink CLAUDE.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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
golink — Go Development Standards
golink is a LinkedIn CLI for humans and LLM agents. Go 1.26.2 on darwin/arm64. See PROMPT_golink.md for the full implementation spec. go.mod, toolchain, and CI config are the source of truth.
Architecture
- CLI: cobra (
github.com/spf13/cobra); auth subcommands:login,status,logout,refresh; org subcommands:list(requiresw_organization_social_feedor legacyw_organization_social); post subcommands:create(with--image,--as-org),list,get,delete,edit,reshare,schedule; top-level:profile,doctor(read-only, not audited),version - Transport seam:
internal/api/transport.go(interface) →official.go(live LinkedIn adapter) /noop.go(fallback). Every CLI command goes throughTransport. - HTTP:
internal/api/client.go—go-retryablehttp, 429/5xx retry,Linkedin-Version+X-Restli-Protocol-Versionheaders, rate-limit parsing, typedapi.Error - Auth: native PKCE OAuth by default with standard OAuth 2.0 fallback (
internal/auth/oauth.go) +go-keyringsession store — tokens never touch disk or logs - Output contract:
schemas/golink-output.schema.json— every--jsonresponse must validate; fixtures ininternal/output/schema_test.go
Packages
main.go entry point + signal handling
cmd/ cobra commands (auth, profile, org, post, comment, react, search, social, batch, approval, schedule, plan, execute, doctor, version)
internal/api/ Transport interface, official adapter, retry client, typed errors
internal/approval/ approval gate (Store interface, FileStore, MemoryStore; states: pending/approved/denied/completed)
internal/audit/ append-only JSONL audit log (Sink interface, FileSink, MemorySink, NoopSink)
internal/auth/ PKCE OAuth + standard OAuth 2.0 fallback + keyring session store
internal/config/ viper settings with env/flag/file precedence
internal/filelock/ cross-process advisory flock helper (sidecar pattern), used by audit/idempotency/schedule/refresh paths
internal/httprecord/ HTTP record/replay cassette (RecordTransport, ReplayTransport, Wrap); sidecar `<path>.lock` flock + fsync on append/save; activated by GOLINK_RECORD / GOLINK_REPLAY
internal/idempotency/ append-only JSONL idempotency store (FileStore, MemoryStore, NoopStore); Store interface includes `Acquire(ctx, key) (release, error)` for per-key cross-process serialisation
internal/output/ JSON envelopes, schema validator, enum parsers
internal/plan/ golink.plan/v1 document type — Load (envelope-aware), SHA256, IsPlannableCommand
internal/privacy/ redaction helpers for persisted audit previews and HTTP record/replay cassettes
internal/schedule/ client-side post queue (Store interface, FileStore, MemoryStore; states: pending/running/completed/failed/cancelled)
schemas/ golink-output.schema.json (the --json contract)
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.
- 5d ago First seen · 159 lines · 2,874 tokens per session scan A 56ed1b8aa597
golink CLAUDE.md is an instructions file published in the GitHub repository mudrii/golink (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,874 tokens to every session, about $0.0144 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
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
unraid-management-agent copilot-instructions.md
Copilot instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
agentcat-go-sdk CLAUDE.md
Claude Code instructions for agentcathq/agentcat-go-sdk, covering claude.md, what this is, build & test commands, module layout and architecture.
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.