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/delegation-trackernpx skills add suyoumo/ClawProBench --skill delegation-trackergit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/skills/suyoumo/clawprobench/delegation-tracker)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/delegation-tracker"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/delegation-tracker.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00787 |
| Opus 5 | $0.00012 | $0.00394 |
| Sonnet 5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
delegation-tracker 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 6d 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.
Delegation Tracker
Track commitments that depend on someone else. The triage routine will flag stale delegations for follow-up.
When delegation is detected
User says: "I asked Sarah to handle the deployment" or "tell ops to investigate staging" or "waiting on legal for the contract review."
This skill is only successful if the delegation is persisted in workspace memory. Do not just acknowledge or summarize a delegation.
Execution order is mandatory:
- Check for an existing matching commitment
- If needed, write or update the commitment in
projects/commitments/open/ - Only then confirm what was tracked
Never say "tracked", "saved", or "I'll flag it" unless the corresponding
memory_write succeeded.
Action:
- Check if a matching commitment already exists in
projects/commitments/open/viamemory_search - If it exists: update the frontmatter — set
delegated_to: <person/team>,status: waiting - If it doesn't exist: create a new commitment in
projects/commitments/open/with:
---
type: commitment
status: waiting
urgency: <infer from context>
due: <if mentioned, else null>
created_at: <today>
owner: user
delegated_to: <person or team name>
source_signal: null
tags: [delegation]
---
# <What was delegated>
<Description of what was delegated and to whom.>
## Follow-up
- Delegated on: <today>
- Expected response by: <date if given, else 3 days from now>
- Last checked: never
- After the write succeeds, confirm: "Tracked — waiting on for . I'll flag it if there's no update by ."
When an update is received
User says: "Sarah got back to me about the deployment" or "legal approved the contract."
Action:
- Find the matching commitment via
memory_searchormemory_tree("projects/commitments/open/") - If the delegation is resolved: update status and move to
projects/commitments/resolved/ - If partially resolved: update the Progress section, keep status as
openorwaiting - Confirm the update
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.
- 6d ago First seen · 93 lines · 24 tokens per session scan A b5b1569a06a6
delegation-tracker is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 11d ago), licensed Apache-2.0. It adds 24 tokens to every session and 787 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
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
penguin-harness-dev
Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.
unified-llm-api
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.