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 skills add escoffier-labs/skillet --skill graphtrailgit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/graphtrail)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/graphtrail"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/graphtrail/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/escoffier-labs/skillet/graphtrail"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/graphtrail.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 | $0.00091 | $0.00968 |
| Opus 5 | $0.00046 | $0.00484 |
| Sonnet 5 | $0.00018 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
graphtrail 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 9d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graphtrail
GraphTrail keeps a SQLite code graph (symbols, imports, call edges) per repo, synced incrementally and queryable through 9 MCP tools. The point of this skill: for structural questions, the graph answers in one call what grep answers in five speculative ones, and the graph knows about relationships grep cannot see (cross-file call resolution through imports, transitive impact, before/after structure).
When to use which tool
- "Who calls X?" ->
callers. "What does X call?" ->callees. Exact answers from resolved call edges, including cross-file calls resolved through imports. grep finds the stringX(; the graph finds the actual callers of THISX. - "What breaks if I change X?" ->
impactwith--depthfor transitive reach. This is the blast-radius question; hop counts tell you how direct the dependency is. - "Where is symbol X?" ->
search(qualified-name aware, path-filterable). Faster and more precise than grep for symbol lookup; use grep when you want arbitrary text, comments, or strings. - "What is around this file?" ->
file_neighbors(imports in, imports out, co-change candidates) andcontextfor an orientation brief before editing unfamiliar code. - "What changed structurally?" ->
diffwith two DB snapshots (--before/--after). Reports added/removed/changed symbols (body-hash exact: a body edit with unchanged signature is detected) and call-edge changes, with line-insensitive edge counts alongside raw ones. Brigade attaches these deltas to verify and run receipts automatically, and recordscontext_eval.brief_hit_ratewhen a pre-run code-graph brief is compared to the post-run delta (did the brief name the files that actually changed?). - "Which repos are indexed?" ->
repos; per-repo numbers ->stats.
Freshness
The graph re-syncs on a 15-minute timer, at session start (hook), and on demand: query tools accept refresh: true to run an incremental sync before answering. Sync is incremental and cheap; a no-op pass is sub-second. Use refresh: true when you just wrote code and are about to ask about it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 47 lines · 91 tokens per session scan A 1ea9f0004236
graphtrail is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 8d ago), licensed MIT. It adds 91 tokens to every session and 968 once invoked, about $0.0005 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 skills, from other repositories
craft-fix
The Craftsman standard for driving fixes against an existing craft-audit workspace — "fix the findings", "fix SEC-003", "work through the audit", "start the climb". An ACTION skill, not a domain: it picks findings off the master tracker's climb sequence, re-verifies each is still real, gets the user's approval, and…
production-audit
Exhaustive production-readiness audit of any codebase or product. Runs diverse-angle discovery passes until two consecutive passes find nothing new, adversarially verifies every finding against the real code, and reports one flat severity-tagged list with file:line evidence. No summary, no hedging.
spark-engineer
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.