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.
git clone --depth 1 https://github.com/mnthe/hardworker-marketplaceWrote 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/commands/mnthe/hardworker-marketplace/ultrawork-lessons)<a href="https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork-lessons"><img src="https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork-lessons/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/commands/mnthe/hardworker-marketplace/ultrawork-lessons"><img src="https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork-lessons.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 | $0.00016 | $0.00472 |
| Opus 5 | $0.00008 | $0.00236 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
ultrawork-lessons 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 9d 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.
What it actually says
Ultrawork Lessons Dashboard
Overview
Display lessons learned from previous ultrawork sessions in this project. Lessons are extracted by the documenter after each session and stored in docs/lessons/.
Usage
/ultrawork-lessons # Show all lessons for current project
/ultrawork-lessons --last 5 # Show 5 most recent
Workflow
-
Find lessons files:
Glob("docs/lessons/*.md") -
Sort by filename (date prefix ensures chronological order), newest first
-
If
--last Nspecified, take only the N most recent files -
For each file, read and display:
- Session Summary (date, tasks, Ralph loops)
- Key Failure-Fix Patterns (pattern name + takeaway)
- Recommendations (actionable items)
-
At the end, show aggregated summary:
- Total sessions with lessons
- Most common failure patterns across sessions
- Top recurring recommendations
Output Format
## Lessons Dashboard
### Recent Sessions
#### 2026-03-18: Auth middleware refactor
- Tasks: 8 (6 first-pass, 2 fix)
- Ralph Loops: 1
- Key lesson: lint를 worker 단계에서 미리 실행할 것
#### 2026-03-15: API endpoint migration
- Tasks: 5 (all first-pass)
- Ralph Loops: 0
- (No failures — clean session)
### Aggregated Insights
- Total sessions: 5
- Average Ralph loops: 0.8
- Most common failure: lint violations (3 sessions)
- Top recommendation: "Run lint before verification"
Edge Cases
- No
docs/lessons/directory -> Display: "No lessons found. Lessons are created after ultrawork sessions complete." - Empty directory -> Same message
- Only clean sessions (no failures) -> Show sessions but note "clean completion"
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.
- 9d ago First seen · 71 lines · 16 tokens per session scan A 9915af96c439
ultrawork-lessons is a command published in the GitHub repository mnthe/hardworker-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 472 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
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.