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/codeinfinity1/stram/agent-self-reflectionnpx skills add CodeInfinity1/Stram --skill agent-self-reflectiongit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00041 | $0.00600 |
| Opus 5 | $0.00020 | $0.00300 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
agent-self-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 yesterday.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Self Reflection
Purpose
Run a model-led reflection over recent work so the assistant can understand what happened, what worked, what failed, and what should change. This is a Stram-owned adaptation of external reference self-reflection patterns.
When To Use
Use after a smoke failure, user correction, long debugging session, complex implementation, or any task where future behavior should improve from evidence.
Inputs And Evidence
- Recent audit runs and notes.
- Current
cognitive_state. - User corrections and preferences.
- Test results, tool failures, and recovery actions.
- Current commitments and follow-ups.
Tool Map
cognitive_self_reviewcognitive_self_review_statuscognitive_interaction_reviewcognitive_interaction_review_statuscognitive_skill_evolvememory_writememory_summary
Workflow
- Gather exact evidence from recent work before reflecting.
- Ask the model to separate facts, uncertainty, risks, user impact, and recommended changes.
- Record durable lessons only when supported by evidence.
- Use skill evolution when the lesson is reusable workflow knowledge.
- Use persona evolution only when the evidence reflects communication style or stable user preference.
- Report a concise reflection with concrete next changes.
Safety And Boundaries
- Do not overfit one incident into a permanent rule.
- Do not hide failures; reflection should surface evidence and limitations.
- Do not claim improvement unless the behavior was changed or recorded.
Safety And Approval
- Reflection must not rewrite durable memory, skills, persona, or commitments without evidence and the native tool's approval/validation path.
- Do not store sensitive or speculative user facts from a single ambiguous event.
- Do not use reflection to justify ignoring the user's newest instruction or active task.
- Keep user-facing reflection concise unless the user asks for a detailed postmortem.
Native Implementation Boundaries
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.
- yesterday First seen · 79 lines · 41 tokens per session scan A 97a08ebd3736
agent-self-reflection is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 600 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 2026-08-31.
Other skills, from other repositories
skills-installer
Install, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled in the current conversation, import a local skill directory or package, search/install from ClawHub, install from a GitHub repo/tree URL, or reconcile conflicts during an upgrade.
omh-jit-learn
This is a Hermes-native jit-learn workflow skill.
omh-instinct-ledger
This is a Hermes-native instinct-ledger workflow skill.
case-study
Craft a portfolio case study with narrative arc, process evidence, and outcomes. Use when telling a project's story to an external audience. For an internal stakeholder deck, use presentation-deck.
xiaohongshu-title
《小红书运营手册 · AI工作台》标题生成与优化技能。用于用户明确要为小红书笔记、封面短句、图文/短视频标题、种草、教程、测评、服务内容起标题、改标题、做标题方向选择时触发。输入可以是正文草稿、选题方向、产品卖点、账号定位、图片/视频描述或已有标题。默认用快速模式输出标题；用户要求分析、首推、理由、方向、诊断或优化时用诊断/优化模式。不要在普通文章标题、论文标题、新闻标题、课程命名等非小红书/社媒场景中自动触发。.
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.