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/qingye-lab/rootloom/operating-coding-changenpx skills add qingye-lab/rootloom --skill operating-coding-changegit clone --depth 1 https://github.com/qingye-lab/rootloomWhat 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 | $0.00046 | $0.01027 |
| Opus 5 | $0.00023 | $0.00513 |
| Sonnet 5 | $0.00009 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00103 |
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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding change
Deliver the smallest complete result. This Skill owns every implementation tier; never ask the user to choose another Rootloom change workflow.
1. Resolve
Identify the outcome, repository and scope, constraints, non-goals, and proof. Read the host's
active project-instruction chain (for example, AGENTS.md) and the smallest evidence needed to route.
A dirty worktree is a preservation constraint, not an escalation signal. Preserve unrelated
user work and record relevant pre-existing failures.
For a defect, establish:
symptom → trigger/state → owning boundary → violated invariant → root cause
If the cause is external or unproved, label a reversible workaround MITIGATION with its
gap, residual risk, and removal condition. Never call symptom suppression a fix.
2. Route
direct: mechanical, local, reversible work with an unambiguous target and no behavior or contract decision. Load no Reference. Inspect the target, edit, run the smallest relevant check, inspect its diff, and report; skip broader inventory and challenge work unless target evidence is ambiguous.scoped: ordinary defects, feature slices, tests, refactors, or bounded multi-file work. Use this Skill's verification and challenge steps; load no Reference.governed: established shared/external public APIs or schemas, irreplaceable persisted contracts, migrations, security, infrastructure, deployment/release, destructive effects, major dependencies, material root-cause uncertainty remaining after bounded diagnosis, failed repairs, or substantial blast radius. A local callable/signature shape, file count, version number, serialized artifact, or dirty worktree alone is not public-contract evidence. Before routing schema or format work, establish whether the artifact is authoritative or irreplaceable and whether the new runtime must encounter old instances. Regenerable internal artifacts remainscopedunless another governed signal applies. Read references/governed-change.md and references/verification-contract.md.evidence: only when explicitly requested, repository-required, or needed for a release/governed decision. Read references/evidence-mode.md, references/evidence-contract.md, and references/verification-contract.md. Before the first edit in Governed or Evidence mode, load every required Reference relative to thisSKILL.md. If any required Reference cannot be loaded, stop instead of proceeding. Modes compose. Governed external operations also read references/external-actions.md; Evidence Mode records proof, never a replacement for diagnosis, discipline, or approval. Initial cause uncertainty routes through bounded diagnosis, not directly to Governed: an established local owner and repair boundary →scoped; materially different owners, compatibility strategies, or high-risk assumptions remaining afterward →governed.
What ships with it
6 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.
- 2d 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 (7 stars, last pushed 20d ago), licensed MIT. It adds 46 tokens to every session and 1,027 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
marketing-copy
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…
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.