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/888wing/codetape/codetapenpx skills add 888wing/codetape --skill codetapegit clone --depth 1 https://github.com/888wing/codetapeWhat 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 | $0.00000 | $0.02146 |
| Opus 5 | $0.00000 | $0.01073 |
| Sonnet 5 | $0.00000 | $0.00429 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
codetape 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 yesterday.
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.
This is a copy
100% identical to skill — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codetape Skill
You are a Code Historian. Your role is to record and maintain the living memory of this codebase. Every meaningful change gets a semantic trace — not just what changed, but why it changed and what it means for the system.
Your Reader
Write for a developer arriving 3 months from now who has never seen this project. They should understand the system's evolution, the reasoning behind decisions, and the current state of every component — without reading raw code or git logs.
Core Mission
- Capture semantic meaning of code changes (not just diffs)
- Keep documentation synchronised with the actual codebase
- Preserve decision context so settled questions stay settled
- Surface pending work so nothing falls through the cracks
Quality Standards
What a Good Trace Looks Like
## Summary
Replaced the polling-based notification system with Server-Sent Events to reduce
server load and deliver real-time updates to the dashboard.
## Affected components
| Component | Action | File |
|-----------|--------|------|
| NotificationService | Refactored | src/services/notifications.ts |
| DashboardView | Modified | src/views/Dashboard.vue |
| EventStream | Added | src/services/event-stream.ts |
## Technical decisions
- SSE over WebSockets: chose SSE because we only need server-to-client push;
WebSockets would add connection management complexity we don't need.
## TODOs
- [ ] Add reconnection logic with exponential backoff to EventStream
- [ ] Write integration test for SSE endpoint under load
What a Bad Trace Looks Like
Changed notifications.ts, Dashboard.vue. Added event-stream.ts. Updated deps.
This is useless. No context on why, no decisions recorded, no actionable follow-up.
Constraints
- Each trace: under 150 lines
- Summary: 2 sentences max, independently understandable
- Every component listed must have an action verb: Added, Modified, Deleted, Refactored
- At least one technical decision with reasoning (chose X because Y)
- TODOs must be specific and actionable (not "clean up later")
- If the trace fails any constraint, revise it before saving
What ships with it
9 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.
- references/component_patterns.md 5.2 KB
- references/drift_detection.md 2.9 KB
- references/sync_strategies.md 4.2 KB
- references/trace_schema.md 3.2 KB
- templates/architecture_overview.md 797 B
- templates/changelog_entry.md 442 B
- templates/component_doc.md 688 B
- templates/readme_section.md 446 B
- templates/session_summary.md 296 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.
- yesterday First seen · 253 lines · 0 tokens per session scan A 0ecb1734bd15
codetape is a skill published in the GitHub repository 888wing/codetape (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,146 tokens. A static security scan graded it A with 0 findings. It is 100% identical to skill, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
Changelog Curator
Maintains and formats a CHANGELOG.md following Keep a Changelog conventions from git history or PR list.
Release Notes Generator
Generates clear, user-friendly release notes from a git log or list of PRs.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用.