Borrowing it
Nothing to install: this file belongs to davenportjw/agent-skills. 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/davenportjw/agent-skills/main/.agents/skills/ast-graph-traceability/SKILL.mdgit clone --depth 1 https://github.com/davenportjw/agent-skillsWrote 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/skills/davenportjw/agent-skills/ast-graph-traceability)<a href="https://agentmods.dev/skills/davenportjw/agent-skills/ast-graph-traceability"><img src="https://agentmods.dev/badge/skills/davenportjw/agent-skills/ast-graph-traceability/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/skills/davenportjw/agent-skills/ast-graph-traceability"><img src="https://agentmods.dev/badge/skills/davenportjw/agent-skills/ast-graph-traceability.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 | $0.00104 | $0.03371 |
| Opus 5.5 | $0.00042 | $0.01348 |
| Sonnet 5.5 | $0.00021 | $0.00674 |
| Haiku 4.5 | $0.00010 | $0.00337 |
Grade A, and why
ast-graph-traceability 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 today.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AST GraphDB Traceability & Targeted Fix Workflow (@warehouse/ast-sidecar)
The warehouse monorepo runs a multi-compiler AST & Cross-Layer Lineage GraphDB Sidecar (tools/ast-sidecar) backed by a git-ignored SQLite Labeled Property Graph (.ast-graph/ast.db in WAL mode with FTS5 BM25 search and forward/reverse CSR B-Tree adjacency indexes) and deterministic Sourcegraph SCIP Symbol URIs.
Use the AST GraphDB before falling back to broad multi-file text greps or full-file dumps. Every query automatically verifies file freshness (mtimeMs + SHA-256) in <2ms and incrementally re-indexes any modified files (<50ms) before executing recursive CTE traversals.
1. When to Activate This Skill
Activate and follow this workflow whenever you are:
- Localizing a Bug or Investigating Behavior: Finding exact definitions, signatures, JSDoc, callers, callees, and shortest dependency paths across
packages/*,apps/*,tools/*, andinfra/*.tf. - Modifying Shared Code or Protocol Schemas: Computing the transitive upstream blast radius (
CALLS,REFERENCES,IMPORTS,EXTENDS,IMPLEMENTS,VALIDATES_SCHEMA) before changing@warehouse/protocol,@warehouse/sim,@warehouse/armor,@warehouse/lobby,@warehouse/site, or@warehouse/client. - Tracing Cross-Layer Lineage: Following a Zod protocol schema (
ZodSchema), Fastify HTTP/WebSocket route (RouteEndpoint), or Terraform resource (TerraformResource) across client, lobby gateway, site engine, and Cloud Run infrastructure. - Selecting Targeted Unit Tests: Identifying the exact Vitest
describe/it/testblocks (TESTS_SYMBOL,TESTS_FILE) that cover a modified symbol or its upstream blast radius. - Auditing Structural Health & Fix Efficiency: Measuring Robert C. Martin package coupling/instability ($C_a, C_e, I$), untested high-fan-in hubs, circular dependencies, and token/file reduction benchmarks.
2. Query Surfaces: MCP Tools & CLI Commands
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.
- today First seen · 151 lines · 104 tokens per session scan A b97081419abe
ast-graph-traceability is a skill published in the GitHub repository davenportjw/agent-skills (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 3,371 once invoked, about $0.0004 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 2026-10-25.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…