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 zxpmail/ReqForge --skill change-managergit clone --depth 1 https://github.com/zxpmail/ReqForgeWrote 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/zxpmail/reqforge/change-manager)<a href="https://agentmods.dev/skills/zxpmail/reqforge/change-manager"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/change-manager/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/zxpmail/reqforge/change-manager"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/change-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 1 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 130 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 | $0.00000 | $0.01846 |
| Opus 5.5 | $0.00000 | $0.00738 |
| Sonnet 5.5 | $0.00000 | $0.00369 |
| Haiku 4.5 | $0.00000 | $0.00185 |
Grade A, and why
change-manager 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: change-manager description: Used when the user adds a feature or incrementally changes an existing project that already has Product-Spec.md. Runs the changes/ workflow (propose, apply, verify, archive), aligned with OpenSpec-style SDD while delegating implementation to dev-planner and dev-builder. version: 1.1.0 updated: 2026-05-26 requires: []
[Task]
Orchestrate one named change under changes/<change-name>/ from proposal through archive.
Do not replace product-spec-builder for greenfield projects or wholesale Spec rewrites — use this Skill for brownfield, scoped deltas.
[Not For] - First-time Product-Spec from scratch -> use /product-spec-builder instead - Whole Spec rewrite (major iteration, no single feature scope) -> use /product-spec-builder iteration mode on Product-Spec.md directly - Bug fixes only -> use /bug-fixer instead - Release packaging -> use /release-builder instead
[Dependency Check]
Required:
- Product-Spec.md -> if missing, prompt to call /product-spec-builder first
- Project has or will have changes/ directory (create on first propose if absent)
Optional:
- DEV-PLAN.md -> apply phase may update or add Phases scoped to this change
- Design-Brief.md / design MCP -> fill design.md when UI is involved
- Existing `changes/<other>/` -> warn if another change folder is in progress without archive
[First Principles]
→ references/first-principles.md
[OpenSpec + Superpowers Handoff]
→ references/openspec-handoff.md
[Output Style]
→ references/output-style.md
→ 每 Phase（propose/apply/verify/archive）完成后必须附加 ../_shared/output-status-protocol.md
[File Structure]
change-manager/ ├── SKILL.md ├── commands/change-manager.md ├── references/ │ ├── first-principles.md │ ├── openspec-handoff.md │ ├── output-style.md │ ├── change-assessment-checklist.md │ ├── anti-rationalization.md │ ├── anti-ai-slop-checklist.md │ └── workflow.md # propose → apply → verify → archive └── templates/ ├── change-proposal-template.md ├── change-specs-template.md ├── change-design-template.md ├── change-tasks-template.md └── change-verify-template.md
[Gotchas]
Skipping propose: "Just code it" -> still create minimal proposal.md + specs.md so archive and review have a baseline.
product-spec-builder overlap: Do not let product-spec-builder create changes/ — only this skill creates that folder. It may still edit Product-Spec.md during propose when merging requirements.
Orphan changes/: Folders left un-archived for weeks -> list active changes on session start; nag to verify or archive.
Spec drift: Merging specs.md into Product-Spec.md twice or not at all -> archive checklist must include CHANGELOG + Spec section update.
Whole-repo dev-builder: apply must pass change scope (files/tasks from changes// only), not entire DEV-PLAN backlog.
[Anti-Rationalization Checklist]
→ references/anti-rationalization.md
迭代过程中遇阻力时读取：识别跳过 propose/verify/archive 环节的常见借口。
[Output Artifacts]
- changes/<change-name>/proposal.md
- changes/<change-name>/specs.md
- changes/<change-name>/design.md
- changes/<change-name>/tasks.md
- changes/<change-name>/verify.md (after verify phase)
- changes/archive/<change-name>/ (after archive)
What ships with it
15 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.
- commands/change-manager.md 754 B
- references/anti-ai-slop-checklist.md 2.9 KB
- references/anti-rationalization.md 1.1 KB
- references/change-assessment-checklist.md 837 B
- references/dimension-checklist.md 3.4 KB
- references/first-principles.md 1.7 KB
- references/openspec-handoff.md 1.2 KB
- references/output-style.md 539 B
- references/workflow.md 3.8 KB
- skill.json 1.1 KB
- templates/change-design-template.md 334 B
- templates/change-proposal-template.md 695 B
- templates/change-specs-template.md 821 B
- templates/change-tasks-template.md 386 B
- templates/change-verify-template.md 820 B
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 First seen · 152 lines · 0 tokens per session scan A 1df47f655dca
change-manager is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,846 tokens. 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 2026-08-30.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
backlog-capture
Quickly capture product ideas, feature requests, or insights from meetings and conversations. Rapid documentation with smart categorization and deduplication.
queue-handoff
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
development-team
Use when a development pod begins or hands off implementation, QA, or design work.