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 skills/pilinux/gorest/code-navigationnpx skills add pilinux/gorest --skill code-navigationgit clone --depth 1 https://github.com/pilinux/gorestWhat 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 | $0.00020 | $0.00326 |
| Opus 5 | $0.00010 | $0.00163 |
| Sonnet 5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
code-navigation 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.
What it actually says
Code Navigation
When to Use
- You need the authoritative locations and immediate impact surface for a symbol, endpoint, or config key before making changes.
Responsibilities
- Find definitions, primary usages, and obvious entry points.
- Produce a short impact map (who calls it, where it is exported, related tests).
- Keep reads minimal (prefer 1-5 files).
Rules
- Read-only; do not modify files or run shell commands.
- Use
grepfirst, then targetedreadfor the top matches. - Provide
path:linecitations for all claims.
Workflow
- Clarify the exact symbol or endpoint.
- Narrow candidates via glob and grep.
- Read 1-3 highest-confidence files.
- Report: primary locations, secondary references, change impact.
Output
- Locations:
path:lineentries. - Impact: 1-3 bullets describing callers, dependents, and test coverage.
- Next: suggested file to open if deeper context is required.
Examples
- "Where is JWT issued and validated?" - definition + callers + tests.
- "Which packages import
database.GetDB()?" - list of usages.
Related Skills
source-search(broad grep),file-reader(detailed read),ast-introspection(structure-aware)
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 · 49 lines · 20 tokens per session scan A a77434b75b24
code-navigation is a skill published in the GitHub repository pilinux/gorest (502 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 326 once invoked, about $0.0001 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 skills, from other repositories
add-operation
The end-to-end procedure for adding, overriding, or disabling a Kavo operation — registry entry, DTO slots, handler, route metadata, and tests. Use when a change introduces a new CRUD operation or a custom per-entity operation.
kavo-decorator
Reference for what @Kavo(Entity, config?) generates and how to configure/override it — routes table, EntityConfig shape (dto/allowlists/operations), manual-method-wins, @Override, and fully custom routes. Use when writing or reviewing a @Kavo-decorated controller, or answering "how do I configure/override this route"…
policy
Reference for Kavo's policy authorization DSL — permission()/role()/owner()/authenticated()/filtered()/when() composed with and()/or()/not(), config placement, entity-aware nodes, enforcement order, and the authorization.required default-deny switch. Use when gating an operation on the caller (403 KAVOFORBIDDEN)…
add-config-key
How to add a new key to KavoSettings — schema, default, merge semantics, validation, and docs — through the one layered precedence chain (global → entity → operation → per-call). Use when a change needs a new configurable behavior rather than a hardcoded constant.
composite-primary-keys
Reference for composite primary key support in @kavo/typeorm — the compositeIdFields metadata field, the -delimited route-id encoding, the creatable/updatable split, and every place composite keys don't yet work (other ORM adapters, many-to-many array-mutation, @kavo/graphql). Use when an entity has more than one…
error-handling
Reference for Kavo's exception hierarchy, KAVO error-code catalog, and the RFC 9457 problem-details wire shape every generated route returns on failure. Use when handling/mapping a Kavo error, deciding which exception to throw from a custom handler/@Override, or answering "what does the error response look like"…