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/feedbackgit 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 | $0.00016 | $0.00481 |
| Opus 5 | $0.00008 | $0.00241 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The continuum feedback queue captures cases where THIS plugin's capabilities forced you to work around something. Items are deduplicated by normalized-title hash; flushing creates GitHub issues via gh (rate-limited).
Subcommands
/continuum:feedback file --title "<short>" --severity minor|major|blocker
Use when, mid-task, you notice "this would have been easier if continuum could ____." Compose the body as:
**Observed limitation:** what's missing or wrong
**Workaround taken:** what you did instead
**Suggested capability:** concrete proposal
**Where it bit me:** link id, file, or step
Then pipe to:
cat <<'CONTINUUM_FB_EOF' | node "$(cat .continuum/.plugin-root)/lib/feedback_cli.js" file --title "$TITLE" --severity "$SEVERITY" --link-id "$LINK_ID"
<body markdown>
CONTINUUM_FB_EOF
Output is JSON: {status: "queued"|"duplicate-pending"|"duplicate-sent", hash, path}.
/continuum:feedback flush [--dry-run]
Flush queued items into GitHub issues. By default rate-limited to 10 per 24h (configurable with --cap). Use --dry-run to preview without creating issues.
node "$(cat .continuum/.plugin-root)/lib/feedback_cli.js" flush ${ARGUMENTS}
Show the resulting JSON to the user. If gh CLI is not installed, the user will need to install it (brew install gh) and run gh auth login before real flushes work.
/continuum:feedback list
Show pending + sent counts.
node "$(cat .continuum/.plugin-root)/lib/feedback_cli.js" list
When NOT to file feedback
- Bugs in OTHER projects → file directly in those projects' issue trackers.
- Conversational gripes ("this prompt was ugly") → not capability gaps.
- One-off papercuts that won't recur → don't pollute the queue.
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 · 55 lines · 16 tokens per session scan A aa7f2bf92052
feedback is a command published in the GitHub repository DevZonayed/Mochi (3 stars, last pushed 15d ago), licensed MIT. It adds 16 tokens to every session and 481 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'.