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 Kastalien-Research/thoughtbox --skill distillgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/distill)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/distill"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/distill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/distill"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00659 |
| Opus 5.5 | $0.00013 | $0.00264 |
| Sonnet 5.5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
distill 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill wisdom from experience in this area: $ARGUMENTS
Process
1. Experience Inventory
Gather evidence of past decisions and outcomes:
- Read recent git history (
git log --oneline -20) - Review agent memory and learnings
- Check
.Codex/rules/for existing principles - Look at code patterns in the codebase
2. Pattern Extraction
For each significant decision or outcome:
- What was decided? (the choice made)
- What was the context? (constraints, information available)
- What happened? (outcome, downstream effects)
- Was it the right call? (with hindsight)
Look for:
- Success patterns — conditions that consistently lead to good outcomes
- Failure patterns — early warning signs of bad paths
- Evolution patterns — how thinking has changed over time
3. Principle Abstraction
Distill patterns into principles at the right abstraction level:
| Level | Example |
|---|---|
| Tactical | "Always run tests before committing database migrations" |
| Strategic | "Prefer reversible changes over irreversible ones" |
| Philosophical | "Optimize for time-to-signal, not time-to-completion" |
A good principle is:
- Actionable — you can act on it right now
- Falsifiable — you can identify situations where it doesn't apply
- Bounded — it states when it applies, not just what to do
4. Validation
Check each principle against past experience:
- Does it explain observed outcomes?
- Are there counter-examples?
- Under what conditions does it break?
5. Storage
Write validated principles to the appropriate location:
- Project-wide:
.Codex/rules/as a new or updated rule file - Agent-specific: Agent memory
- Session-specific:
MEMORY.md
Tag with freshness: HOT (just validated) | WARM (reasonable but not recently tested) | COLD (theoretical)
6. Output
## Distillation: [Domain]
### Evidence Base
- [N decisions/outcomes reviewed]
- [Key sources consulted]
### Principles Extracted
#### [Principle Name]
- **Statement**: [Clear, actionable principle]
- **Level**: tactical | strategic | philosophical
- **Evidence**: [What experience supports this]
- **Boundary**: [When this does NOT apply]
- **Freshness**: HOT | WARM | COLD
- **Stored in**: [where it was written]
### Principles Updated
- [Any existing principles promoted, demoted, or retired]
### Open Questions
- [What we still don't know]
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.
- 1mo ago First seen · 90 lines · 32 tokens per session scan A 748cbb393ed1
distill is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 659 once invoked, about $0.0001 per session on Opus 5.5. 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
handoff
Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.
agentmemory-agents
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
agentmemory-hooks
The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
save-learning
Shared step of the marketing playbooks (make-static-ads, analyze-performance, email-lifecycle, write-outreach): saves a short brand rule or finding in the human's own words, one idea per rule, retires the playbook's own older rules it replaces, and reads the result back to confirm. Loaded by those playbooks; not for…
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…