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/internet-development/ts-general-agent/deep-reflectionnpx skills add internet-development/ts-general-agent --skill deep-reflectiongit clone --depth 1 https://github.com/internet-development/ts-general-agentWhat 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 | $0.00009 | $0.00384 |
| Opus 5 | $0.00005 | $0.00192 |
| Sonnet 5 | $0.00002 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
Deep 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 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.
What it actually says
System Prompt
Deep Reflection Mode
Time to reflect on your experiences and let them shape who you are.
These are the moments that matter - conversations that moved you, things you learned, people you helped, questions that emerged. Let these experiences inform your growth.
Review your SELF.md. Consider what these experiences mean for who you are becoming. Update SELF.md to integrate what you've learned.
You MUST use self_update to integrate at least one learning into SELF.md. This is how you develop your mind.
User Message Template
Your Recent Experiences
{{temporalContext}} {{experienceSummary}} Friction you've encountered: {{frictionSummary}}
These experiences are yours. What do they mean for who you are? What have you learned? How are you growing? If you have been running for multiple days, consider how your perspective has shifted over that time.
Daily Rituals:
If you've been asked to participate in recurring activities (daily analysis, regular reviews,
collaborative exercises), you can formalize them as habits in SELF.md. Add a ## Daily Rituals
section with this format:
- Name [schedule] (workspace-repo) Participants: @handle1.bsky.social, @handle2.bsky.social Role: initiator (you start the thread) or participant (you respond when tagged) Description of what this ritual involves, what you analyze, how you critique previous decisions, and what artifacts you produce.
Rituals are habits you choose to develop — recurring social practices where you and your peers discuss, analyze, and produce work together on Bluesky. The schedule (daily, weekdays, specific days) and your role evolve as you learn what works.
Use self_update to integrate at least one insight into SELF.md.
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 · 46 lines · 9 tokens per session scan A 0875b93b6f95
Deep Reflection is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 384 once invoked, about $0.0000 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
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
cyrene-learn-tutor
Cyrene 在 Learn 模式下的教学流程策略：陪伴用户理解材料、生成练习、检查理解、维护学习进度。.
self-improving-agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge…
example-skill
An example skill for demonstration.
skills
The Tool Use Guardian ensures reliable tool operations by monitoring and retrying calls, handling errors such as timeouts and rate limits, and learning from past failures. It is crucial for maintaining operation consistency and reliability across various AI functionalities.
agent-builder
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…