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/m98/fluent/fluent-session-analyzernpx skills add m98/fluent --skill fluent-session-analyzergit clone --depth 1 https://github.com/m98/fluentWhat 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 | $0.00064 | $0.01359 |
| Opus 5 | $0.00032 | $0.00679 |
| Sonnet 5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
fluent-session-analyzer 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Analyzer
Overview
Every practice session writes a markdown report to /results/{skill}-session-{ID}.md (e.g. writing-session-012.md). This skill describes how to read those files to plan adaptive follow-up practice. Use it when the tutor needs narrative context the JSON databases don't capture — the exact sentence the learner wrote, the scenario, the feedback they received.
When to Use
Load this skill whenever the tutor:
- Plans today's focus before
/fluent-learn,/fluent-writing, etc. - Answers the learner's question "what's my weakest area" or "what should I work on".
- Generates the next session plan.
Skip this skill when aggregated JSON numbers are enough — prefer read-db.py for counts, trends, and mastery levels. Use this skill only when the textual context matters.
Instructions
1. Find recent session files
/results/{skill}-session-{ID}.md
File naming: {skill}-session-{NNN}.md keeps files grouped by skill + chronological by ID. Read the most recent 3-5 files of the relevant skill; don't re-read the entire history.
2. Extract error patterns
Scan for ❌ markers. Each correction has:
- The wrong form ("Your answer")
- The correct form
- A category (grammar, formal_informal, vocabulary, prepositions, articles, spelling, missing)
- A severity (🔴 critical, 🟡 moderate, 🟢 minor)
Count frequency per pattern across recent files:
- 1 occurrence — possibly a typo, ignore
- 2-3 — emerging pattern, worth drilling
- 4+ — critical weakness, highest priority
3. Extract strengths
Scan for ✅ markers and scores ≥ 7/10. Note consistent correct usage — these are reinforcement targets, not drill targets.
4. Track trajectory
Across sessions, track:
- Overall accuracy per session
- Critical vs moderate vs minor error counts
- Writing speed (words per minute, if tracked)
5. Plan the next session
Based on the analysis:
- Top 3 critical weaknesses (highest frequency + severity) → 50% of session time.
- Top 2 moderate patterns → 30% of session time.
- One full integration scenario → 20% of session time.
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 · 142 lines · 64 tokens per session scan A 17089e41d43c
fluent-session-analyzer is a skill published in the GitHub repository m98/fluent (381 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,359 once invoked, about $0.0003 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 2026-08-30.
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…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.