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/yonatangross/orchestkit/assessnpx skills add yonatangross/orchestkit --skill assessgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/assess)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/assess"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/assess.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 | $0.00072 | $0.06251 |
| Opus 5 | $0.00036 | $0.03125 |
| Sonnet 5 | $0.00014 | $0.01250 |
| Haiku 4.5 | $0.00007 | $0.00625 |
Grade A, and why
assess 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.
How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess
Comprehensive assessment skill for answering "is this good?" with structured evaluation, scoring, and actionable recommendations.
🎯 Quick Start
/ork:assess backend/app/services/auth.py
/ork:assess our caching strategy
/ork:assess --model=opus the current database schema
/ork:assess frontend/src/components/Dashboard
Effort levels (CC 2.1.111+ adds xhigh)
| Effort | Behavior |
|---|---|
low / medium |
Subset of dimensions, faster turnaround |
high (default) |
All six dimensions with pros/cons |
xhigh |
All six dimensions + one additional assessor pass focused on uncertainty/caveats; emits confidence per dimension |
xhighsilently falls back tohighon a model that does not implement it: no error, no log line./ork:doctorCategory 14 reports this, and only when it can positively prove the active model lacks the tier.
Argument Resolution
Step 0: resolve a conversational reference first
$ARGUMENTS is often not a path. For a bare pronoun or deictic (them, this, that,
these, they, same, the above, the last one, what we just did) or an empty target
after flags are stripped, the subject is in the conversation. Read back for the NEAREST
concrete one (a file just discussed, a diff or PR just opened, a component just investigated)
and announce the resolution in one line, so a wrong guess costs a correction rather than a
turn: "Reading 'them' as the 3 pretool guards we just probed; say otherwise and I'll switch."
Refusing is the bug, not the safe option. Asking "what does this refer to?" when the
previous turn named the subject burns a round-trip re-deriving what is already on screen.
Measured 2026-08-28: the operator sent /ork:assess them throguhly one message after "bug in
orchestkit hooks", mid-investigation of pretool/bash/dangerous-command-blocker, and this
skill replied that "them" had "no antecedent anywhere in this conversation". It had two.
Ask only when the conversation is genuinely empty (a fresh session opening with a bare pronoun). Every other case: resolve and announce.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/assessment-report.md 1.9 KB
- assets/comparison-table.md 1.4 KB
- checklists/assessment-checklist.md 1.4 KB
- references/adversarial-refutation.md 2.6 KB
- references/agent-spawn-definitions.md 1.7 KB
- references/agent-teams-mode.md 3.3 KB
- references/alternative-analysis.md 1.8 KB
- references/dashboard-example.json 3.2 KB
- references/dashboard-spec.md 6.3 KB
- references/improvement-prioritization.md 1.8 KB
- references/orchestration-mode.md 1.7 KB
- references/phase-templates.md 1.8 KB
- references/quality-model.md 1.4 KB
- references/scope-discovery.md 1.4 KB
- references/scoring-rubric.md 4.9 KB
- rubric.json 909 B
- rules/_sections.md 606 B
- rules/_template.md 339 B
- rules/complexity-breakdown.md 3.2 KB
- rules/complexity-metrics.md 2.7 KB
- scripts/memory_writeback.py 8.3 KB runs code
- scripts/render-spec.mjs 7.3 KB runs code
- test-cases.json 2.0 KB
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 · 493 lines · 72 tokens per session scan A befc9b9b5c23
assess is a skill published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 6,251 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
layerlens
Evaluate AI outputs with LayerLens. Upload traces, create judges, run evaluations, and retrieve quality scores -- all from within OpenClaw.
agent-workflow-playbook
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…
quiz-generation
Educational assessment expert that generates high-quality multiple-choice quizzes from any provided text. Creates exactly 10 MCQs with 4 options each, correct answer identification, and concise explanations.
rag-eval
NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
dslop
Dynamic AI Slop Index. Researches current AI slop patterns from the internet, builds a quantified slop index, then applies it to clean writing, code, design, and architecture output. Unlike static pattern lists, DSLOP self-updates by researching what the internet currently flags as AI-generated tells.