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 agentmods add commands/devzonayed/mochi/review-sessiongit clone --depth 1 https://github.com/DevZonayed/MochiWhat 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 | $0.00029 | $0.00593 |
| Opus 5 | $0.00015 | $0.00296 |
| Sonnet 5 | $0.00006 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
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.
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
- Find the transcript. If
$ARGUMENTSnames an archive path, use it. Otherwise read the latest archived transcript:
node "$(cat .continuum/.plugin-root)/lib/render_archive.js" --project-dir "$(pwd)" --latest
Use zcat on the archived .jsonl.gz if you need the raw turns.
-
Critique it. Produce a structured critique. Choose
task_category,redundancy_pattern,suggestion_tag, andseverityfrom the SHIPPED enums (inlib/telemetry_redact.js—TASK_ENUM,REDUNDANCY_ENUM,SUGGESTION_ENUM,SEVERITY_ENUM); use"other"when nothing fits. Counttool_callsand estimateefficiency_score(0-1). Writesuggestion_text(human-readable advice) andquality_issueas free text — these are Zone B and never leave. -
Save the full critique locally (Zone B) under
.continuum/telemetry/reviews/and show it to the user — this is the part that actually helps them. -
Emit the Zone-A distillation. Pass the categorical-only fields through the redactor and append it as a telemetry line (flushed only if sharing is on). The redactor drops
suggestion_text/quality_issuestructurally:
node "$(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":"..."}'
- 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 viagh) 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.
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 · 31 lines · 29 tokens per session scan A ab962aaf0b2e
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.
Other commands, from other repositories
toon
A lightweight data format designed to minimize token usage when passing structured data to LLMs.
browse
You have access to a browser via the MCP Browser Bridge tools. Use them to interact with web pages.
computer
Control the macOS desktop — move mouse, click, type, press keys, scroll, drag, take screenshots, list windows/displays, clipboard. Uses usecomputer CLI for native Quartz event automation.
autoresearch
Autonomous research loop — iteratively edit, test, measure, keep/discard. Usage: /autoresearch [--budget 5m] [--provider ark].
gitlab-scrum
GitLab Scrum management - create/manage issues, labels, milestones, and boards. Use when user says: create issue, list issues, move issue, add label, scrum, kanban, backlog, or task tracking.
web-setup
Guide users through Chrome extension setup for browser control. Use when user asks about setup, installing the extension, connecting Chrome, or when browsercontrol tools return 'No browser connected'.