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/ssbun/csl-agent-kit/task-lessonsnpx skills add SSBun/csl-agent-kit --skill task-lessonsgit clone --depth 1 https://github.com/SSBun/csl-agent-kitWhat 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 | $0.00090 | $0.01908 |
| Opus 5 | $0.00045 | $0.00954 |
| Sonnet 5 | $0.00018 | $0.00382 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
task-lessons 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prevent Repeated Mistakes
Use tasks/lessons.md as the canonical current set of reusable preventive controls. A Lesson is learned only when it changes future behavior: matching work recognizes its Trigger, follows its Rule, and satisfies its Check. Recording, displaying, or reading one is not completion.
Boundaries
Route information to its proper owner. Prefer eliminating the failure or enforcing prevention in source, schema, types, tests, lint, CI, or a mandatory workflow when that can work without Agent judgment. A Lesson is the last-mile behavioral control for the judgment that remains; never use one as a substitute for an enforceable invariant.
- Reusable, judgment-dependent workspace prevention rules belong in
tasks/lessons.md. - Task-specific decisions, progress, results, and evidence belong in the owning task record.
- Stable workspace structure and relationships belong in
tasks/context.md. - Cross-workspace preferences or persistent directives belong in the applicable global rule mechanism.
- Procedures belong in an SOP or runbook.
- Speculation, secrets, duplicates, and one-off details are not stored.
Routine lesson maintenance does not create a task record.
Admission Gate
Store or retain a Lesson only when every condition holds:
Reusable: the correction prevents a class of mistakes beyond the current task.Preemptive: an Agent can recognize the Trigger before the failure recurs.Preventive: the Rule directly changes behavior and blocks the failure mechanism rather than patching one symptom.Verifiable: the Check can show that the preventive control covers the relevant scope.Last-mile: stronger mechanical enforcement does not fully remove the need for Agent judgment.Correctly routed: Lessons is the right carrier under the boundaries above.
If a stronger control fully removes the judgment, use or propose it through the appropriate owning task and choose No-op for Lessons. If judgment remains, record only the residual behavior.
What ships with it
4 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 · 139 lines · 90 tokens per session scan A f41cc9129740
task-lessons is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 1,908 once invoked, about $0.0005 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…