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 skills add digital-stoic-org/agent-skills --skill pick-harnessgit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote 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/digital-stoic-org/agent-skills/pick-harness)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/pick-harness"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/pick-harness/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/skills/digital-stoic-org/agent-skills/pick-harness"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/pick-harness.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 | $0.00195 | $0.02483 |
| Opus 5 | $0.00097 | $0.01241 |
| Sonnet 5 | $0.00039 | $0.00497 |
| Haiku 4.5 | $0.00019 | $0.00248 |
Grade B, and why
pick-harness scanned grade B with 1 finding 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- 🔑 **Isolation and auth are coupled.** `--setting-sources ""` strips `~/.claude/settings.json`, often where the 3P auth env lives → the clean room silently kills its own auth (`apiKeySource:"none"` → "Not logged in"). How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick Harness
Friction-driven judge for which guardrail to add next — then scaffolds it. Sibling of /pick-model (the model) and /pick-workflow (the topology). Grows a harness one guardrail at a time to fit the real failure; never designs a full harness upfront. When: an agent keeps failing at X · you want to stop it doing Y · you're starting a task and want a minimal starter set.
Extends the repo's
HARNESS-ENGINEERING.md(Böckeler/Fowler guides⏩ vs sensors⏪, computational⚙️ vs inferential🧠) with 2 axes (latency, timing) +🧱 containment. Single source of truth for the which-guardrail call — don't re-derive the grid elsewhere. Worked examples, sandbox detail, drive-templates →reference.md.
Decision grid — 4 axes + 1 orthogonal
| Axis | Ask | Values |
|---|---|---|
| Role | Orient or inspect? | 🪧 guide (persuades, bypassable) · 🚨 sensor (observes, returns a verdict) |
| Nature | Deterministic or judgment? | ⚙️ computational (code/regex/exit code) · 🧠 inferential (an LLM judges) |
| Timing | Before or after damage? | ⏩ feedforward (preventive) · ⏪ feedback (corrective) |
| Latency | Tokens burned before the catch? | ⚡ immediate (before generation) · 🐌 deferred (after the fact) |
| 🧱 Containment (orthogonal) | — | Makes the action impossible. Neither guides nor inspects — the 4 questions don't apply. |
Feedback ladder (by latency): self-correction⚡ (test/lint, pre-commit) → human-review🧑 (at the PR) → pipeline🐌 (E2E agent-browser / LLM-judge, post-integration).
CORE PRINCIPLE — classify by LATENCY, not sophistication. Prescribe the earliest catch that fits, not the fanciest. The best sensor makes the bug unrepresentable (
newtype Seconds ≠ Millis→ a whole bug class becomes a compile error, free forever). A cheap ⚡ guard beats a clever 🐌 one.
Flow — diagnose → prescribe → scaffold
- Classify input. Friction ("X keeps failing") → the ONE next guardrail (default). Task ("starting X") → a minimal starter set (≈1 feedforward guide + 1 containment), not a full harness.
- Diagnose — reason across all 4 axes at once (they interact): preventable before the act → ⏩guide, else ⏪sensor · a rule/regex/exit-code decides → ⚙️computational, else semantic → 🧠inferential · can it be made impossible/unrepresentable? → 🧱 containment (type/schema/sandbox/permission-deny), the earliest catch there is — prefer it when available.
- Prescribe one grid point + honest latency/cost rationale: why this catch-point, not an earlier (impossible?) or later (wastes tokens?) one.
- Scaffold the artifact, then self-check: dry-run it in the sandbox mode the rule below selects (
--safe-modeunless a carve-out applies), report whether it fires on the failing case. A deterministic artifact (script/filter) dry-runs against a synthetic fixture — no model call, no auth needed.
What ships with it
1 file 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.
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.
- 10d ago First seen · 82 lines · 195 tokens per session scan B 6d9a7a20f4bd
pick-harness is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 195 tokens to every session and 2,483 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.