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 qingye-lab/rootloom --skill operating-coding-changegit clone --depth 1 https://github.com/qingye-lab/rootloomWrote 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/qingye-lab/rootloom/operating-coding-change)<a href="https://agentmods.dev/skills/qingye-lab/rootloom/operating-coding-change"><img src="https://agentmods.dev/badge/skills/qingye-lab/rootloom/operating-coding-change/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/qingye-lab/rootloom/operating-coding-change"><img src="https://agentmods.dev/badge/skills/qingye-lab/rootloom/operating-coding-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 8 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 | $0.00027 | $0.00809 |
| Opus 5.5 | $0.00011 | $0.00324 |
| Sonnet 5.5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
operating-coding-change 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding change
Implement the user's requested outcome within the active repository guidance and authorized scope. A question or review alone does not authorize a repair. Preserve unrelated changes; a dirty worktree is a preservation constraint, not a reason to stop or escalate.
Diagnose and route
Read the smallest evidence needed to identify the owner and verification boundary. For a defect, connect the observed trigger, violated invariant, root cause, and proposed repair. Initial uncertainty calls for bounded diagnosis; escalate only when materially different owners, compatibility choices, or high-risk assumptions remain. Label an unproved workaround as mitigation and explain its limitation and removal condition.
Choose the route internally; do not ask the user to choose a workflow:
direct: mechanical, local, reversible work. Inspect, edit, and check the target; no Reference or separate challenge pass is required.scoped: bounded defects, features, tests, refactors, and documentation. Use the checks below without loading additional References by default.governed: changes affecting security, production, infrastructure, destructive effects, major dependencies, established public APIs, irreplaceable persisted contracts, or a materially uncertain blast radius. Read governed-change.md and verification-contract.md before dependent edits. Regenerable internal artifacts, file count, and keyword mentions alone do not trigger this route; identify real consumers and changed behavior.evidence: only on explicit request or an applicable repository requirement. Read evidence-mode.md, evidence-contract.md, and verification-contract.md. Evidence records proof; it does not grant authority or replace diagnosis.
For deployment, release, infrastructure, production data, or other external execution, read external-actions.md. Verify exact authorization; preserve explicit approval gates and do not infer permission for destructive actions, purchases, credential/permission changes, incompatible contracts, or scope expansion. If a required procedure or authorization is unavailable, stop only the dependent action and continue independent authorized work. Platform and hard-deny controls remain authoritative.
What ships with it
8 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.
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.
- 1mo ago Changed · -22 lines · -19 tokens per session 3beb5933cb64
- 1mo ago First seen · 91 lines · 46 tokens per session scan A 23881dfcb9e5
operating-coding-change is a skill published in the GitHub repository qingye-lab/rootloom (10 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 809 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
readiness
Use when the user wants to analyze, audit, or assess their codebase for AI agent readiness. Also use for "readiness report", "how ready is my project", "analyze my codebase", "audit my repo", "check my setup", or "what should I improve".
template-comprehensive-assessment
Full checkout audit for the Research Project Template — tests, architecture, docs, manuscript, pipeline. USE WHEN user asks for comprehensive assessment, full repo review, health check across projects, audit everything, or pre-merge sanity sweep for template exemplars — even without naming docs/prompts or a skill. Not…
pr-sweep
Review every open PR with the code-reviewer agent and an adversarial review, apply the findings, and merge each one once CI is green. Use when asked to ship, sweep, or merge open PRs.
slop-check
LLM-judge slop & erosion scan of a diff, mirroring SlopCodeBench. Scores code on Erosion (verbosity, dead branches, redundant structure accumulated under iterative change) and Verbosity (unnecessary complexity), then reports per-category findings weighted toward code that EXTENDS existing modules. Use after…
agentic-code-review
Use when reviewing a diff, pull request, branch, or AI-generated code for correctness, security, regression, test, performance, and maintainability risks before merge.
repo-health-check
Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.