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.
git clone --depth 1 https://github.com/rosudrag/ai-praxisWrote 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/commands/rosudrag/ai-praxis/introspect)<a href="https://agentmods.dev/commands/rosudrag/ai-praxis/introspect"><img src="https://agentmods.dev/badge/commands/rosudrag/ai-praxis/introspect.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00885 |
| Opus 5 | $0.00000 | $0.00443 |
| Sonnet 5 | $0.00000 | $0.00177 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
introspect 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/introspect - Audit Past Conversations for Improvements
Analyze recent Claude Code conversation transcripts to identify friction points, missing docs, skill gaps, and behavioral corrections.
Instructions
1. Gather Transcripts
List recent conversation transcripts sorted by size (larger = more work = more signal):
ls -lS "{{transcripts_path}}" --time=ctime | grep ".jsonl" | head -15
Pick the 5-8 largest/most recent transcripts for analysis.
2. Extract User Messages
For each transcript, extract user messages to understand what was asked, corrected, and repeated:
import json
with open('<transcript>.jsonl', 'r', encoding='utf-8', errors='ignore') as f:
for line in f:
d = json.loads(line)
if d.get('type') == 'user':
content = d.get('message', {}).get('content', '')
# Extract text from string or list content
Look for patterns:
- Corrections: "no", "wrong", "not that", "I said", "stop"
- Repeated asks: Same question asked 2+ times
- Interruptions: "[Request interrupted by user]"
- Frustration signals: profanity, ALL CAPS, "!!!", short terse corrections
- Manual workflows: Multi-step operations the user guided step-by-step
3. Spawn Analysis Agents
For large transcripts (>500KB), spawn background agents to analyze each one in parallel. Each agent should extract:
- Tasks/topics discussed
- Friction points — things the user had to repeat, correct, or re-explain
- Manual workflows that could be automated with a skill command
- Missing documentation that would have prevented confusion
- User corrections/feedback — exact quotes when possible
4. Cross-Reference Existing Setup
Check what already exists before recommending duplicates:
- Existing skills:
{{commands_path}}/*.md - Existing memories:
{{memory_path}}/*.md - AGENTS.md / CLAUDE.md rules
- Serena memories (if installed):
.serena/memories/*.md
5. Categorize Findings
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.
- 8d ago First seen · 100 lines · 0 tokens per session scan A fef9f3631bc6
introspect is a command published in the GitHub repository rosudrag/ai-praxis (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 885 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.