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/kastalien-research/thoughtbox/workflow-reflectionnpx skills add Kastalien-Research/thoughtbox --skill workflow-reflectiongit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWhat 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 | $0.00033 | $0.01370 |
| Opus 5 | $0.00016 | $0.00685 |
| Sonnet 5 | $0.00007 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
workflow-reflection 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 3d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the reflection and finalization stage. $ARGUMENTS
Purpose
You are executing Stage 8 (Reflection) of the development workflow. The implementation is reviewed, revised, and compounded. Your job is to finalize: reflect on what happened, move artifacts to their permanent locations, close tracking issues, and prepare the branch for merge.
Pre-Conditions
Before starting, verify:
.workflow/state.jsonexists andcurrentStageis"reflection"- Stages 1-7 are all completed or skipped (check state file)
- All sub-agent work has been committed (no uncommitted implementation changes)
Process
Step 1: Agent Structured Reflection
Review the entire workflow by reading the state file and any persisted summaries. Produce a structured reflection:
WORKFLOW REFLECTION
====================
Workflow: <id> - <title>
Branch: <branch>
Duration: <startedAt> to now
## What Worked
- [specific things that went well, with evidence]
- [approaches that should be repeated]
## What Didn't Work
- [specific things that went poorly, with evidence]
- [approaches to avoid in future]
## Hypothesis Outcomes
- H1 "<text>": VALIDATED / REFUTED / INCONCLUSIVE
- H2 "<text>": ...
## Revision Iterations
- Total: N/3
- Root causes of revision: [what triggered each iteration]
## Unexpected Discoveries
- [things learned that weren't part of the original plan]
- [codebase behaviors that surprised us]
## Process Improvements
- [suggestions for improving the workflow itself]
Step 2: User Reflection (Optional)
Ask the user if they want to add their own reflection:
Would you like to add your own reflection notes?
This is optional but valuable for the compound learning record.
If the user provides input, append it to the reflection under a ## Chief Agentic Notes section.
Step 3: Move ADR to Permanent Location
Based on the workflow outcome:
If hypotheses were validated (happy path):
- Move the spec with frontmatter to accepted:
# Historical: ADRs archived — update spec status in frontmatter instead of mv .adr/<NNN>-<name>-adr.md .adr/accepted/<NNN>-<name>.md - Move associated summaries with it:
# Historical: ADRs archived — update spec status in frontmatter instead of mv .adr/<NNN>-<name>-summary-*.md .adr/accepted/ - If the spec was in staging, move it to
specs/ - If any existing docs in
specs/ordocs/decisions/archive/adr/accepted/are now outdated by this work, update them
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.
- 3d ago First seen · 185 lines · 33 tokens per session scan A 9b6952b49100
workflow-reflection is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,370 once invoked, about $0.0002 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
reasoning
Use BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare…
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.