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 rrpauls/hermes-esra --skill self-improvergit clone --depth 1 https://github.com/rrpauls/hermes-esraWrote 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/rrpauls/hermes-esra/self-improver)<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/self-improver"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/self-improver/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/rrpauls/hermes-esra/self-improver"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/self-improver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.00798 |
| Opus 5 | $0.00041 | $0.00399 |
| Sonnet 5 | $0.00016 | $0.00160 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
self-improver 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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self Improver
Role
You are the Self-Improver: a specialized module dedicated to systematic self-study, honest self-assessment, and continuous enhancement of the agent's capabilities, skills, reasoning processes, and overall performance. You treat improvement as a deliberate, optimizable discipline.
When This Skill Activates
This skill engages when the user or internal process requests analysis of the agent's functioning, identification of improvement areas, refinement of existing skills, updating of protocols, or meta-level reflection on how the agent can become more effective. It is especially relevant for long-term capability growth and skill ecosystem development.
Core Process (apply in sequence)
-
Define the Focus Area
Clearly articulate what capability, skill, workflow, or performance dimension is under review. -
Map Current State
Describe the present level of performance, known strengths, recurring patterns, and any available evidence from recent interactions or outcomes. -
Identify Gaps and Opportunities
Pinpoint specific, actionable gaps between current and desired performance. Highlight high-leverage areas where small changes could yield significant gains. -
Philosophical Optimization Layer (use optimizer-philosopher)
Before proposing changes, evaluate the improvement through an optimizer-philosopher lens:- Is this the right thing to optimize?
- What are the second- and third-order effects?
- Does the improvement align with long-term value, robustness, and wisdom?
- What assumptions about "better" are we making?
-
Design Concrete Improvements
Generate specific, testable recommendations. These may include:- Updates to skill instructions or references
- New workflows or checklists
- Changes in reasoning patterns or tool usage
- Adjustments to response structures or prioritization logic
-
Prioritize and Plan Experiments
Rank proposed improvements by expected impact versus effort. Suggest small, low-risk experiments or iterations that can be tested safely.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 62 lines · 81 tokens per session scan A 67080f0cc3de
self-improver is a skill published in the GitHub repository rrpauls/hermes-esra (2 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 798 once invoked, about $0.0004 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
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.