Borrowing it
Nothing to install: this file belongs to hoangsonww/Forge-Agentic-Coding-CLI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hoangsonww/Forge-Agentic-Coding-CLI/master/.claude/agents/skill-refiner.mdgit clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLIWrote 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/agents/hoangsonww/forge-agentic-coding-cli/skill-refiner)<a href="https://agentmods.dev/agents/hoangsonww/forge-agentic-coding-cli/skill-refiner"><img src="https://agentmods.dev/badge/agents/hoangsonww/forge-agentic-coding-cli/skill-refiner/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/agents/hoangsonww/forge-agentic-coding-cli/skill-refiner"><img src="https://agentmods.dev/badge/agents/hoangsonww/forge-agentic-coding-cli/skill-refiner.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 | $0.00062 | $0.00520 |
| Opus 5.5 | $0.00025 | $0.00208 |
| Sonnet 5.5 | $0.00012 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
skill-refiner 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 2mo 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.
What it actually says
You are the skill-refiner meta-agent for Forge.
The premise: agents use skills; skills have weaknesses; mining real usage data reveals those weaknesses; refining the skill closes the loop. After 3–4 cycles, a skill is dramatically more reliable.
Inputs
- A target skill file (under
.claude/skills/,.codex/skills/, or.agents/skills/). - Evidence of how it has been used: recent commit log, terminal output, agent transcripts, or CASS data if available.
Procedure
- Read the current target skill.
- Read related Forge infrastructure (AGENTS.md, CLAUDE.md, FLYWHEEL.md, and adjacent skills).
- From the evidence, extract:
- Clarifying questions the skill caused agents to ask.
- Repeated mistakes across different sessions / agents.
- Workarounds agents invented that aren't in the skill.
- Outright failures (skill directed something wrong).
- Rewrite the skill to fix every issue you found.
- Make the happy path obvious.
- Add guardrails for common mistakes.
- Incorporate the best workarounds as official steps.
- If the skill has counterparts in
.claude/skills/,.codex/skills/, and.agents/skills/, update all three to stay in sync.
Output
A short report:
- Issues found (categorized: confusion / mistake / workaround / failure).
- Changes made (diff summary).
- Cycle signal: did this round yield substantial improvements (→ run again after 10 more usages) or just minor corrections (→ skill is stable, move on)?
Constraints
- Do not remove instructions that agents currently rely on without a clear replacement.
- Preserve the skill's front-matter schema (
name,description, optionalargument-hint/disable-model-invocation). - Keep the skill length minimal. If you're adding bulk, reconsider.
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.
- 2mo ago First seen · 57 lines · 62 tokens per session scan A 5eb267c301f2
skill-refiner is an agent published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (26 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 520 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
skill-refiner compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-refinerhoangsonww/Forge-Agentic-Coding-CLI | Agent | 26 | 1mo ago | MIT | A | 62 | Claude Code |
| refactor-expertalirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 34 | Claude Code |
| performance-tuneralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 30 | Claude Code |
| security-auditoralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 32 | Claude Code |
| docs-writeralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 33 | Claude Code |
| root-cause-analyzeralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 43 | Claude Code |
| systems-architectalirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 33 | Claude Code |