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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/walkindude/gosymdb/agents-md"><img src="https://agentmods.dev/badge/instructions/walkindude/gosymdb/agents-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 | $0.00867 | $0.00867 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
gosymdb 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — gosymdb
Documentation for AI agents (and anyone else) reading this repo.
What gosymdb is
gosymdb is a Go-specific symbol and call-graph database backed by SQLite. It uses Go's own type-checker (go/packages, go/types) to build a persistent index of one or more Go modules, then answers structured queries:
find— search symbols by name, package, file, or kinddef— exact single-symbol lookupcallers/callees— direct or transitive call edgesblast-radius— full transitive impact (with test/prod split)dead— symbols with no callersimplementors— interface ↔ type satisfactionreferences— where a type appears (assertions, switches, literals, conversions)packages,health,agent-context,version— meta queries
Every query supports --json for structured output. The full API is enumerated in one shot by gosymdb agent-context, which prints a JSON document with command signatures, flags, env block, and parsing notes.
How the database is found
gosymdb walks parent directories looking for gosymdb.sqlite, the same way Go tools walk for go.mod. Pass --db <path> to override. If no database is found, commands return error_code: no_database with a hint to run gosymdb index --root <module> first.
The freshness loop
The index goes stale the moment source files change. Every JSON response carries an env.stale_packages array listing packages whose source has drifted from what's indexed. The check uses a git fast-path (one git diff against the commit stamped at index time) with a per-file FNV-64a hash fallback when git isn't usable.
Pass --auto-reindex to any query command to re-index stale modules in place before the query runs. The check itself is cheap enough to run on every call (sub-second on Kubernetes-scale codebases).
MCP integration
gosymdb exposes gosymdb cli-bridge-manifest — a single subcommand that prints the canonical cli-bridge spec for this binary. When cli-bridge is installed and gosymdb's spec is registered, each command becomes an MCP tool named gosymdb_<command> (e.g. gosymdb_callers, gosymdb_blast_radius). Setup steps are in the main README's MCP section.
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.
- 4d ago First seen · 51 lines · 867 tokens per session scan A b158cf0daeb3
gosymdb AGENTS.md is an instructions file published in the GitHub repository walkindude/gosymdb (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 867 tokens to every session, about $0.0043 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
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.
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 AGENTS.md
AGENTS.md instructions for PlunderStruck/scip-query, covering scip-query and git workflow.
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.