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 sergeyklay/.agents --skill improve-selfgit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/sergeyklay/.agents/improve-self)<a href="https://agentmods.dev/skills/sergeyklay/.agents/improve-self"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/improve-self/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/sergeyklay/.agents/improve-self"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/improve-self.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 15 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 126 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00211 | $0.03505 |
| Opus 5 | $0.00105 | $0.01752 |
| Sonnet 5 | $0.00042 | $0.00701 |
| Haiku 4.5 | $0.00021 | $0.00350 |
Grade A, and why
improve-self 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 5d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improving Self by Closing Skill Gaps
This skill turns the trace of just-completed work into a question: was there a procedure I should have had written down? When the answer is yes, it scaffolds a candidate Agent Skill into the current project — with the human approving every write.
The discipline is conservative by design. A skill created for a one-off question becomes long-term noise in the activation context of every future task. A skill created without checking existing skills becomes a duplicate and a confusion vector. A skill encoding version-specific or transient behavior becomes a permanent footgun. The bar for creation: a concrete, recurring, procedural gap that survived a check against every existing skill, with the user signing off on the draft.
Running scripts bundled with this skill
Script paths are resolved relative to this SKILL.md, not the agent's CWD. If a relative command (for example python3 scripts/discover_skills.py) fails to resolve, prefix it with the directory the platform loaded SKILL.md from.
Fallback. If python3 is missing or the script cannot be located, every procedure here ships a manual alternative — follow that instead.
What counts as a gap
A gap is procedural and recurring. Not every difficulty is a gap.
| Pattern in the trace | Skill-shaped? |
|---|---|
| The agent repeated the same 3-step lookup three times in one task | Yes |
| The agent figured out a non-obvious investigation workflow from scratch and it worked | Yes |
| The agent recovered from an error by inventing a procedure that should be reusable | Yes |
| The user corrected the agent's approach with "no, here we always do X first" | Yes |
| The agent realized mid-task it lacked a playbook other agents would also face | Yes |
| The agent did not know a fact ("what is the Kafka default port?") | No — research gap, not skill gap |
| The agent failed once and recovered easily | No — one-off, not recurring |
| The task was complex but succeeded smoothly | No — complexity ≠ missing procedure |
| The agent had to consult unfamiliar library docs | No — that is what research-it is for |
| The task succeeded without struggle | No — nothing to fix |
What ships with it
4 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.
- 5d ago Changed · -5 tokens per session 46b5ea1d04b4
- 9d ago First seen · 166 lines · 216 tokens per session scan A 9be49185c475
improve-self is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 211 tokens to every session and 3,505 once invoked, about $0.0011 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
chatdoc-studio-api
ChatDOC Studio API usage guide - complete documentation and examples for PDF parsing, chat applications, agent applications, content retrieval, and data extraction APIs.
war-room
Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detection are enforced every turn via the persistent-persona skill.
system-info
Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.
persistent-persona
Mechanism for keeping an agent anchored to a caller-defined persona across sessions. Covers the biplate private memory system for drift detection and self-correction.
memory-checkpoint
Defines how to save and load agent state as checkpoint files.
ChatDOC Studio--KnowledgeMate
Create and operate ChatDOC Studio knowledge bases through pdrouter using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base…