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 sd0xdev/sd0x-harness --skill generate-runnergit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/generate-runner)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/generate-runner"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/generate-runner/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/sd0xdev/sd0x-harness/generate-runner"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/generate-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 119 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 145 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 183 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.02091 |
| Opus 5 | $0.00032 | $0.01045 |
| Sonnet 5 | $0.00013 | $0.00418 |
| Haiku 4.5 | $0.00006 | $0.00209 |
Grade A, and why
generate-runner 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 5d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Runner
Trigger
- Keywords: generate runner, create runner, custom runner, eject runner, runner for python, runner for rust, runner for go
When NOT to Use
| Need | Use Instead |
|---|---|
| Run precommit checks | /precommit or /precommit-fast |
| Install existing runner | /project-setup (auto-installs) |
| Configure the shipped runner's lint globs | Check first that the runtime runner has no @generated_at header, then edit .claude/runner-config.json — and set lintArgMode for the same script role, or the globs stay inert (see § Lint Argument Injection) |
Lint Argument Injection
Scope: the runners this plugin ships — scripts/precommit-runner.js and
scripts/verify-runner.js. What /precommit, /precommit-fast and /verify actually execute is
the runtime copy at .claude/scripts/*, installed by /install-scripts. A runner generated by
this skill is written to the same path but is user-owned: its template does not append lint
arguments, so lintGlobs / lintArgMode have no effect on it. The discriminator is the eject
header (§ Step 4) — all three of @generated_at, @plugin_version, @template, each on its own
line with a value, in the opening comment block. Read the file before configuring it.
Known limitation. A project that installed a runner before this fix keeps running the old
version, which passes ESLint-only flags into whatever lint script the repo declares — a
file-rewriting non-ESLint linter reads them as paths and edits sources. Fixing the plugin source
does not reach that copy, and detecting it reliably needs per-release provenance, which is
deliberately out of scope. Remedy: /install-scripts precommit-runner.js verify-runner.js --force, with --dry-run first to read the write set (the installer copies "scripts +
dependencies" without defining the closure, so the dry run is the authoritative list). The runners
are named rather than swept in by --all, which would force-overwrite every core script; confirm
lib/utils.js — where the fixed runners decide whether to inject — appears in the report.
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.
- 5d ago First seen · 185 lines · 64 tokens per session scan A e44b19b0c2fc
generate-runner is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 2,091 once invoked, about $0.0003 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
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
update
Safe cc10x upgrade that preserves local modifications. Stashes diffs, pulls upstream, rebuilds cache, rebases patches. Use this skill when: updating cc10x, upgrading, pulling latest cc10x, syncing plugin, refreshing cache, or checking for new versions. Triggers: update cc10x, upgrade cc10x, pull cc10x, sync plugin…
generator-fix-integrator
Internal Auto-Harness generator skill for worktree-merge fix integration. Use only inside the parallel Generator integrator when it is addressing named defects from QA or retest.
comet-archive
A workflow for the fifth stage of Comet Classic: archiving a completed change, merging its specification updates, and finishing the branch. It uses Comet commands and a fixed layout for tracking the change.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.