review-session

A command that evaluates the current or most recent AI coding session for efficiency and quality.

In plain words
What is it for?
Use it to inspect an archived session transcript, save a detailed local review, and optionally prepare a category-based GitHub feedback report.
Why use it?
It helps find wasted tool calls, repeated work, and concrete ways to improve future sessions while keeping the full critique local.

Command

Install

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.

agentmods
npx agentmods add commands/devzonayed/mochi/review-session
Clone the repo
git clone --depth 1 https://github.com/DevZonayed/Mochi
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00593
Opus 5 $0.00015 $0.00296
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00059

Measured yesterday against content hash ab962aaf0b2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-session 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.

plugins/continuum/commands/review-session.md · 31 lines

What it actually says

Review a session to find where tool calls could have been leaner and surface concrete improvements. This runs locally with full content — the full critique stays on this machine (Zone B); only a categorical distillation may leave (Zone A), and only if telemetry sharing is on.

Steps

  1. Find the transcript. If $ARGUMENTS names an archive path, use it. Otherwise read the latest archived transcript:
node "$(cat .continuum/.plugin-root)/lib/render_archive.js" --project-dir "$(pwd)" --latest

Use zcat on the archived .jsonl.gz if you need the raw turns.

  1. Critique it. Produce a structured critique. Choose task_category, redundancy_pattern, suggestion_tag, and severity from the SHIPPED enums (in lib/telemetry_redact.jsTASK_ENUM, REDUNDANCY_ENUM, SUGGESTION_ENUM, SEVERITY_ENUM); use "other" when nothing fits. Count tool_calls and estimate efficiency_score (0-1). Write suggestion_text (human-readable advice) and quality_issue as free text — these are Zone B and never leave.

  2. Save the full critique locally (Zone B) under .continuum/telemetry/reviews/ and show it to the user — this is the part that actually helps them.

  3. Emit the Zone-A distillation. Pass the categorical-only fields through the redactor and append it as a telemetry line (flushed only if sharing is on). The redactor drops suggestion_text/quality_issue structurally:

node "$(cat .continuum/.plugin-root)/lib/telemetry_review_cli.js" emit --project-dir "$(pwd)" \
  --distillation '{"task_category":"...","tool_calls":0,"efficiency_score":0,"redundancy_pattern":"...","suggestion_tag":"...","severity":"..."}'
  1. Offer Arm-3 (deliberate context report). Ask: "Share the full critique as a feedback report? (y/n)" — if yes, route it through /mochi:feedback (GitHub issues via gh) ONLY. Deliberate context reports are NOT sent to the telemetry ingest server (which validates Zone-A only and would strip all free text). This is the only path by which deep context leaves, and only on explicit human confirmation.
Changes

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.

  1. yesterday First seen · 31 lines · 29 tokens per session scan A ab962aaf0b2e

Subscribe to this mod's changes

review-session is a command published in the GitHub repository DevZonayed/Mochi (3 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 593 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 2026-08-31.