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/technicalpickles/pickled-claude-plugins/reflectgit clone --depth 1 https://github.com/technicalpickles/pickled-claude-pluginsWhat 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 | $0.00010 | $0.00864 |
| Opus 5 | $0.00005 | $0.00432 |
| Sonnet 5 | $0.00002 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
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 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect on This Conversation
Help capture a retrospective of this conversation. You'll analyze what happened, ask the user a few questions, then generate a structured reflection document.
Step 1: Analyze the Conversation
Review the conversation so far and identify:
Failed Attempts
What was tried and didn't work? How was each failure resolved?
- Look for error messages, retries, or approaches that were abandoned
- Note what the resolution was (user correction, different approach, etc.)
Corrections Made
Where did the user provide feedback that changed direction?
- Explicit corrections ("no, do it this way")
- Redirections ("let's try something else")
- Clarifications that revealed a misunderstanding
Skills Activated
Which skills were invoked during this conversation?
- Look for Skill() tool calls
- Look for announcements like "I'm using the X skill"
- Note the skill names
Key Decisions
What significant choices were made about approach, tools, or architecture?
- Why was each decision made?
- Were alternatives considered?
Hook Interventions
Were any tool calls blocked or redirected by hooks?
- What was blocked?
- What was the workaround?
@reflect Notes
Scan user messages for @reflect tags — these are observations the user wanted captured.
- Collect all
@reflect <note>entries - These are proactive observations, not corrections
Step 2: Ask the User
Ask these questions to get the user's perspective. Use the AskUserQuestion tool with all questions at once:
Q1 - Outcome: "Did we accomplish what you set out to do?"
- Options: Fully complete / Partially complete / Blocked / Abandoned
Q2 - Approach: "How did the approach feel? Any decisions that seemed off?"
- Open-ended text
Q3 - Skills: (Only if skills were used) "Did any skills help or get in the way?"
- Options: Helped / Got in the way / Mixed / No opinion
Q4 - Friction: "Where did you have to intervene or correct course?"
- Open-ended text
Step 3: Generate the Retrospective
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 · 128 lines · 10 tokens per session scan A 0ac9e900ee9a
reflect is a command published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 864 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 commands, from other repositories
OPSX: Onboard
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
OPSX: Bulk Archive
Archive multiple completed changes at once.
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Verify
Verify implementation matches change artifacts before archiving.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Archive
Archive a completed change in the experimental workflow.