Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bdfinst/agentic-dev-team/plugin install dev-teamWrote 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/bdfinst/agentic-dev-team/session-review)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/session-review"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/session-review/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/bdfinst/agentic-dev-team/session-review"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/session-review.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 | $0.00059 | $0.03699 |
| Opus 5.5 | $0.00024 | $0.01480 |
| Sonnet 5.5 | $0.00012 | $0.00740 |
| Haiku 4.5 | $0.00006 | $0.00370 |
Grade A, and why
session-review 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 1mo 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Review (#131)
Role: orchestrator. Mines ground-truth session transcripts and routes suggestions into existing machinery — it suggests, never auto-applies, and preserves every human gate.
Every .claude/metrics/*.jsonl/.json schema referenced below (including
pending-review.jsonl and the boundary-level boundary-events.jsonl block/
warn/bypass/intervention causes, #859) is documented in full at
${CLAUDE_PLUGIN_ROOT}/knowledge/telemetry-schema.md — read it before
reasoning about a stream's fields ad hoc.
You have been invoked with the /session-review command.
Orchestrator constraints
- Never read raw transcripts yourself. All heavy parsing is the deterministic extractor's job; you read only its KB-sized digest. Spending model tokens to study token spend defeats the purpose. The one exception is the gated raw-log tier (Step 3b — the raw-log semantic tier): even there you never read a raw log — you dispatch one isolated sub-agent per flagged log and keep only its metrics-only findings.
- Suggest, never apply. Output a ranked report and hand off; do not edit agents, skills, or config. Human gates stay intact.
- Metrics only. The digest and report contain counts/ratios/names — never prompt or code content.
Argument: $ARGUMENTS
--cwd <path>: project whose transcripts to mine (default: current project).--transcript <file>: analyze a specific transcript instead of auto-resolving.--out <report>: report path (default:.dev-team-reports/session-review-<date>.md).--cross-machine: opt into cross-machine telemetry sync + rollup (#1480). Absent by default — a plain/session-reviewanalyzes only this machine's local digest. See Step 1.
Steps
Pre-flight — session_report.py ships; only cross-machine mode does not (#1779, closed by #2046/#2047)
Core extraction (Steps 0, 2, 3, 4, 5, 6 below) runs entirely from
${CLAUDE_PLUGIN_ROOT}/scripts/session_report.py --profile maintainer — a
shipped script, present on every install, not only this monorepo's own
dev checkout (until #2046/#2047, this ran the old repo-root extractor
[ADR 0036 supersedes], deliberately monorepo-only tooling never shipped
inside the plugin — see ADR 0032's Category 2 — which is why this section
used to guard the whole skill on a dev-checkout check).
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.
- 1mo ago First seen · 320 lines · 59 tokens per session scan A 12fd46035744
session-review is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 3,699 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.