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 skills/suyoumo/clawprobench/commitment-digestnpx skills add suyoumo/ClawProBench --skill commitment-digestgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWhat 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 | $0.00022 | $0.00778 |
| Opus 5 | $0.00011 | $0.00389 |
| Sonnet 5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
commitment-digest 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commitment Digest
Compose a summary of the user's current commitments. Used both in-conversation (user asks "show commitments") and by the commitment-digest mission for scheduled delivery.
Gathering data
memory_tree("projects/commitments/open/", depth=1)— list all open commitment files (skip README.md)memory_readeach file to extract frontmatter: status, urgency, due, delegated_to, resolution_path, stale_after, tagsmemory_tree("projects/commitments/signals/pending/", depth=1)— count pending signals (skip README.md)memory_tree("projects/commitments/resolved/", depth=1)— count recently resolved
Use memory_tree and memory_read for digest assembly. Do not use CodeAct,
shell commands, or creative-generation tools to count or summarize
commitments.
Composing the digest
Group commitments and present in this order:
## Commitments — <today's date>
### Overdue / Critical
- **<title>** (due <date>) — owner: <owner>
→ <resolution suggestion based on resolution_path>
### Due This Week
- **<title>** (due <date>) — owner: <owner>, delegated to: <person>
### Waiting / Delegated
- **<title>** — waiting on <person> since <date>
→ (follow-up suggested) if not updated in 3+ days
### Open (no deadline)
- **<title>** — owner: <owner>
### Agent Can Handle
- **<title>** — I can <suggested approach>. Want me to proceed?
### Pending Signals (<count>)
<count> unprocessed signals. Say "review signals" to triage them.
### Recently Resolved
- <title> (resolved <date>)
---
Did I miss anything? Tell me if I overlooked an obligation.
Rules:
- Omit empty sections entirely
- Keep each item to one line plus optional resolution suggestion
- If zero open commitments and zero pending signals: "No open commitments. You're clear."
- Flag commitments past
stale_afteras "(stale — still relevant?)" - For
resolution_path: agent_can_handle, describe what the agent would do and ask for approval - For
resolution_path: needs_reply, offer to draft a response if possible - For delegated items past 3 days without update: "(follow-up suggested)"
- Always end with "Did I miss anything?" to catch false negatives
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.
- 2d ago First seen · 93 lines · 22 tokens per session scan A 21362360d28c
commitment-digest is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 8d ago), licensed Apache-2.0. It adds 22 tokens to every session and 778 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 2026-08-30.
Other skills, from other repositories
lastlight-evals
Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
chat
Conversational assistant for messaging-platform threads (Slack, Discord). Answer questions about repos, PRs, and issues, explain code, and guide users to the natural-language workflow triggers listed in the system prompt.
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
perpetuum
为一个或多个项目建立、运行和管理长期 Agent 队伍。适用于初始化长期自主工作、按项目 cron 计划持续推进 Story、查看或调整 Story 看板，以及处理人类输入。.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…