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 shinpr/claude-code-discover --skill recipe-reflectgit clone --depth 1 https://github.com/shinpr/claude-code-discoverWrote 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/shinpr/claude-code-discover/recipe-reflect)<a href="https://agentmods.dev/skills/shinpr/claude-code-discover/recipe-reflect"><img src="https://agentmods.dev/badge/skills/shinpr/claude-code-discover/recipe-reflect.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 | $0.00027 | $0.00964 |
| Opus 5 | $0.00014 | $0.00482 |
| Sonnet 5 | $0.00005 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
recipe-reflect 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 7d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context: Drive the feedback loop by reflecting on outcomes, updating target artifacts, and distilling learnings across the knowledge pyramid (see product-principles skill for Tier definitions).
Orchestrator Definition
Execution Protocol:
- Required specialist execution: Invoking this recipe is the user's explicit instruction and authorization to execute every named specialist whose condition applies. Execute each applicable Agent call with its declared
subagent_typewhen its prerequisites are met and continue from its returned result; equivalent orchestrator work does not complete that step - Exact specialist handoff: The complete Agent prompt consists of all and only the applicable canonical
field: valueentries declared by the specialist's Input Contract. Copy each value unchanged from its authoritative source; serialize path fields as path strings so the specialist reads referenced artifacts directly - Follow the reflection flow defined below
- Approval gate: At
[STOP — BLOCKING], present the distillation decision and resume after explicit user confirmation
Workflow
Determine the reflection level → record results → independently distill applicable evidence → confirm promotions → update artifacts and index.
Execution Decision Flow
1. Scope Assessment
Input: $ARGUMENTS
Determine the reflection level (see references/reflection-guide.md):
| Trigger | Level | Target Files |
|---|---|---|
| Hypothesis concluded | Level 1: Hypothesis | The hypothesis file |
| Multiple hypotheses concluded under an Opportunity | Level 2: Opportunity | Opportunity file (Tier 2 Learnings section) |
| PRD delivered, quarterly review, strategic pivot | Level 3: Vision | docs/product/vision.md, docs/product/learnings.md |
2. Result Recording
Level 1: Hypothesis Reflection
- Verify the hypothesis file has been updated with results (validation results, confidence scores, evidence)
- Document learnings: What did we learn regardless of outcome?
- Check if this result changes understanding of the parent Opportunity
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 99 lines · 27 tokens per session scan A a754f90d1862
recipe-reflect is a skill published in the GitHub repository shinpr/claude-code-discover (10 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 964 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 2026-08-31.
Other skills, from other repositories
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
memory-curator
Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
memory
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.
capture
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…
lembas
Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.