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 yu-iskw/coding-agent-fabric --skill improve-claude-configgit clone --depth 1 https://github.com/yu-iskw/coding-agent-fabricWrote 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/yu-iskw/coding-agent-fabric/improve-claude-config)<a href="https://agentmods.dev/skills/yu-iskw/coding-agent-fabric/improve-claude-config"><img src="https://agentmods.dev/badge/skills/yu-iskw/coding-agent-fabric/improve-claude-config/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/yu-iskw/coding-agent-fabric/improve-claude-config"><img src="https://agentmods.dev/badge/skills/yu-iskw/coding-agent-fabric/improve-claude-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.00497 |
| Opus 5 | $0.00018 | $0.00249 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
improve-claude-config 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Claude Configuration
Purpose
This skill enables Claude Code to evolve and improve its own configuration based on observed patterns, user feedback, and development needs.
When to Use
Invoke this skill when:
- You've explained the same concept to Claude multiple times
- Claude repeatedly makes the same type of mistake
- A new workflow pattern has emerged that should be automated
- Hooks could prevent recurring issues
- New skills would benefit the project
Self-Improvement Workflow
1. Analyze Current State
Read and understand the current configuration:
# View CLAUDE.md
read_file CLAUDE.md
# List all skills
list_dir .claude/skills/
# List all agents
list_dir .claude/agents/
# View current hooks
read_file .claude/settings.json
2. Identify Improvement Opportunity
| Pattern | Action |
|---|---|
| Repeated explanation | Add to CLAUDE.md or create a skill |
| Recurring mistake | Add rule to CLAUDE.md |
| Manual repetitive task | Create a hook |
| Complex workflow | Create a skill |
| Specialized task delegation | Create an agent |
3. Implement Improvement
Adding Rules to CLAUDE.md
For project conventions or gotchas Claude keeps forgetting:
## Recent Learnings (append to CLAUDE.md)
- [Date]: Description of rule and why it matters
Creating a New Skill
- Create directory:
.claude/skills/<skill-name>/ - Create
SKILL.mdwith standard structure.
Creating a New Hook
Add to .claude/settings.json and create the corresponding script in .claude/hooks/.
4. Validate Changes
- Verify JSON syntax in
settings.json. - Test hooks if added.
- Verify skill loads correctly.
Best Practices
- Be minimal: Only add what's necessary
- Be specific: Vague rules are ignored
- Test changes: Validate hooks and skills work
- Version control: Commit configuration changes with clear messages
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.
- 9d ago First seen · 85 lines · 36 tokens per session scan A 7add71534a7f
improve-claude-config is a skill published in the GitHub repository yu-iskw/coding-agent-fabric (1 stars, last pushed 8d ago), licensed Apache-2.0. It adds 36 tokens to every session and 497 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
delegate-coding-agent
Route coding work to another local coding-agent CLI through the llm-provider MCP server. Use when a task benefits from a powerful model for difficult reasoning or a faster, lower-cost model for bounded implementation, tests, investigation, or review.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.
waybill
Alias for the Waybill handoff workflow. Use when the user asks for /waybill, /waybill export, or /waybill import.