Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/skills/validate-session-schemas/SKILL.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/validate-session-schemas)<a href="https://agentmods.dev/skills/rajbos/ai-engineering-fluency/validate-session-schemas"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/validate-session-schemas/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/rajbos/ai-engineering-fluency/validate-session-schemas"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/validate-session-schemas.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 | $0.00096 | $0.02193 |
| Opus 5.5 | $0.00038 | $0.00877 |
| Sonnet 5.5 | $0.00019 | $0.00439 |
| Haiku 4.5 | $0.00010 | $0.00219 |
Grade A, and why
validate-session-schemas 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 yesterday.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Session Schemas Skill
Validates that recent session log files on the current machine still match the schema our parsers expect, per supported platform, and surfaces new fields that appeared on disk but aren't documented/used yet.
It answers two questions in one pass:
- Did anything break? — Drift detection against a small set of fields our
parsers actually depend on ("contracts"). A missing required field on an
observed record type is a
DRIFTfailure. - Is there new information to use? — Any field observed on disk that is not in the known baseline ("knownFields") is reported as a new field. These are candidates for new features or better token attribution (e.g. real token counts, new model metadata, new event types).
Why this skill exists
The pre-existing copilot-log-analysis skill (analyze-session-schema.ps1)
only covered VS Code Copilot Chat JSON + Copilot CLI JSONL + OpenCode, with
crude substring-based "new field" detection. It did not loop per supported
platform, had no recency window, and didn't cover JetBrains, Claude Code,
Gemini CLI, or Antigravity. This skill closes that gap.
Platforms covered
The source of truth for supported platforms is
src/adapters/adapterRegistry.ts. This skill validates the
file-based JSON/JSONL ecosystems that have schema docs under
docs/logFilesSchema/:
| Platform id | Editor / tool | Format | Discovery root |
|---|---|---|---|
copilot-chat |
VS Code Copilot Chat | json / jsonl | VS Code variants workspaceStorage/*/chatSessions, globalStorage |
copilot-cli |
Copilot CLI | jsonl | ~/.copilot/session-state/ |
jetbrains |
JetBrains Copilot | jsonl | ~/.copilot/jb/{uuid}/partition-*.jsonl |
claude-code |
Claude Code | jsonl | ~/.claude/projects/{hash}/*.jsonl |
gemini-cli |
Gemini CLI | jsonl | ~/.gemini/tmp/*/chats/session-*.jsonl |
antigravity |
Antigravity | jsonl | ~/.gemini/antigravity/brain/*/.system_generated/logs/transcript.jsonl |
opencode |
OpenCode | json / jsonl | <xdg-data>/opencode/storage/session/**/ses_*.json; also opencode.db (SQLite, via node:sqlite) |
mistral-vibe |
Mistral Vibe | json | <VIBE_HOME or ~/.vibe>/logs/session/*/meta.json (only meta.json; messages.jsonl is never read) |
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.
- yesterday First seen · 166 lines · 96 tokens per session scan A b5de2a6a0381
validate-session-schemas is a skill published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 2,193 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 2026-10-26.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
observability-langsmith
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…