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 commands/axiomantic/spellbook/reflexion-analyzegit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/reflexion-analyze)<a href="https://agentmods.dev/commands/axiomantic/spellbook/reflexion-analyze"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/reflexion-analyze.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 | $0.00022 | $0.01051 |
| Opus 5 | $0.00011 | $0.00526 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
reflexion-analyze 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflexion Analysis Pipeline
Invariant Principles
- Every feedback item is processed - Do not skip items regardless of severity; minor patterns compound into systemic failures
- Root causes, not symptoms - Categorize by underlying cause (knowledge gap, fabrication, process skip); surface-level fixes lead to repeated failures
- Reflections persist across sessions - Stored lessons must be retrievable by future attempts; a lesson learned but not stored is a lesson wasted
Inputs
| Input | Required | Description |
|---|---|---|
feature_name |
Yes | Feature that received ITERATE verdict |
feedback |
Yes | List of feedback items from roundtable |
stage |
Yes | Stage where iteration occurred |
iteration_number |
Yes | Current iteration count |
Step 1: Parse Feedback
Each feedback item has: source (archetype), stage, return_to, critique, evidence, suggestion, severity, iteration.
Parse every item. Extract all structured fields.
Step 2: Categorize Root Cause
| Category | Indicators | Pattern |
|---|---|---|
| Incomplete Analysis | Missing cases | Discovery too shallow |
| Misunderstanding | Wrong interpretation | Requirements ambiguity |
| Technical Gap | Wrong API/approach | Knowledge limitation |
| Scope Creep | Added complexity | Boundary discipline failure |
| Quality Shortcut | Missing tests | Time pressure/oversight |
| Integration Blind Spot | Interface mismatch | System thinking gap |
Fractal exploration (optional): When the same root cause category appears in 2+ feedback items, invoke fractal-thinking with intensity explore and seed: "Why does [failure pattern] keep recurring despite [previous corrections]?". Use the synthesis to identify systemic root causes beyond the fixed category table.
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 · 124 lines · 22 tokens per session scan A fc8547110d5b
reflexion-analyze is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,051 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
namespaces
List and explain available memory namespaces.
prompts
Work with MCP prompt templates for memory operations.
capture
Capture a memory (decision, learning, pattern, or context) to persistent storage.
recall
Search persistent memories using semantic, hybrid, or text search.
sync
Sync memories with git remote (deprecated - SQLite is now authoritative).