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/walkindude/gosymdb/claude-mdgit clone --depth 1 https://github.com/walkindude/gosymdbWrote 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/walkindude/gosymdb/claude-md)<a href="https://agentmods.dev/instructions/walkindude/gosymdb/claude-md"><img src="https://agentmods.dev/badge/instructions/walkindude/gosymdb/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 | $0.01400 | $0.01400 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
gosymdb 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on gosymdb
This is the gosymdb repo. The binary built here is the typed Go symbol index, and running it against this codebase is the canonical way to navigate, since the schema and command surface match the source you're editing.
What gosymdb does for navigation
gosymdb resolves symbols via Go's go/packages and go/types (the loader and typechecker the compiler uses), not by string matching. For Go-semantic questions ("who calls X", "what implements Y", "what breaks if I change Z") it returns concrete answers with file paths, line numbers, and fully-qualified names. Grep finds string occurrences; gosymdb finds resolved symbols. The two answer different questions, and either is the right tool depending on what's being asked.
Session-start bootstrap
gosymdb agent-context
agent-context always emits JSON with the full command reference plus an env block (cwd, db path, stale_packages, git state). Reading it once at the top of a session removes the need for --help calls later.
If env.db is empty, no database has been built. The path that fixes this:
gosymdb index --root . --db gosymdb.sqlite
gosymdb agent-context # env.db now populated
After that, subsequent commands auto-discover the database from cwd or its ancestors; an explicit --db flag is only needed for non-default paths.
Navigation tasks and the corresponding command
| Task | Command |
|---|---|
| Where is this symbol defined? | gosymdb def FuncName --json |
| What calls this function? | gosymdb callers --symbol <fqname> --json |
| What does this function call? | gosymdb callees --symbol <fqname> --json |
| What's in this file? | gosymdb find --file <path> --json |
| What's in this package? | gosymdb find --pkg <pkg> --json |
| List all symbols in the DB | gosymdb find --json (up to --limit) |
| What implements this interface? | gosymdb implementors --iface <name> --json |
| What breaks if I change this? | gosymdb blast-radius --symbol <fqname> --json |
| List all packages | gosymdb packages --json |
| Index quality report | gosymdb health --json |
| Dead code candidates | gosymdb dead --pkg <prefix> --json |
| Where is this type used? | gosymdb references --symbol <name> --json |
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 · 100 lines · 1,400 tokens per session scan A e3205823728c
gosymdb CLAUDE.md is an instructions file published in the GitHub repository walkindude/gosymdb (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,400 tokens to every session, about $0.0070 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
gograph AGENTS.md
AGENTS.md instructions for ozgurcd/gograph, covering agents.md, project authority and conditional scrinium use.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
scip-query AGENTS.md
AGENTS.md instructions for PlunderStruck/scip-query, covering scip-query and git workflow.
kartograf AGENTS.md
Instructions for dev-manul/kartograf, covering agents.md, what this is, build & test, layout and hard-won rules (do not relearn these the hard way).
scip-query CLAUDE.md
Claude Code instructions for PlunderStruck/scip-query, a project described as: Evidence and verification for AI coding agents: map code, reuse concepts, finish migrations, and gate diffs.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.