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 OpenMinis/MinisSkills --skill self-improving-agentgit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/self-improving-agent)<a href="https://agentmods.dev/skills/openminis/minisskills/self-improving-agent"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/self-improving-agent/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/openminis/minisskills/self-improving-agent"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/self-improving-agent.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 | $0.00083 | $0.03450 |
| Opus 5.5 | $0.00033 | $0.01380 |
| Sonnet 5.5 | $0.00017 | $0.00690 |
| Haiku 4.5 | $0.00008 | $0.00345 |
Grade A, and why
self-improving-agent scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh --project /var/minis/workspace/my-project error "curl request failed" "HTTP 429" How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement Skill (Minis Edition)
This skill is used in the Minis environment to record errors, corrections, and reusable best practices, creating a traceable learning loop.
Minis Directory Conventions
- Working directory:
/var/minis/workspace/ - Default learning log directory for this skill:
/var/minis/skills/self-improving-agent/data/ - Public learning log directory within this skill (after promotion):
/var/minis/skills/self-improving-agent/data/public/ - Project-level learning log directory (optional):
<project>/.learnings/ - Learning log files:
LEARNINGS.md(corrections, knowledge gaps, best practices)ERRORS.md(command failures, exception output)FEATURE_REQUESTS.md(new capabilities requested by users)
By default, log entries go first to the skill's own
datadirectory. When you explicitly specify a project, write to the project-level log. When an issue has been abstracted into a cross-project rule, promote it to the skill's public area or the Minis memory system.
Current Final Rules
- Default logging location:
/var/minis/skills/self-improving-agent/data/ - Public area within the skill:
/var/minis/skills/self-improving-agent/data/public/ - Project-level logging: Use
<project>/.learnings/only when--project <path>is passed explicitly - Recommended public parameter:
--public - Compatibility alias:
--workspaceis still available, but only for compatibility and is no longer recommended - Promotion behavior:
promote <entryID>copies the entry to the public area within the skill, automatically marks the source entry aspromoted, and writes back**Promoted to**and### Resolution Record - Duplicate protection: If the entry already exists in the skill's public area, running
promoteagain will not append a duplicate
Quick Reference
| Scenario | Action |
|---|---|
| Command or operation fails | Log to the skill directory by default: data/ERRORS.md |
| The user corrects you | Log to the skill directory by default: data/LEARNINGS.md, category correction |
| The user needs a missing capability | Log to the skill directory by default: data/FEATURE_REQUESTS.md |
| Project context is explicitly specified | Log to <project>/.learnings/ |
| External API or tool fails | Log to ERRORS.md in the current scope, including integration details |
| Knowledge is outdated | Log to LEARNINGS.md in the current scope, category knowledge_gap |
| A better solution is found | First log it to the current scope, then promote it after confirming it is generally applicable |
| Similar issues recur across multiple projects | Promote to the public area within the skill: data/public/ |
| Similar to an existing entry | Link with **See Also** and consider raising the priority |
| Widely applicable experience | Promote to the public area within the skill or to Minis memory. See "Promoting to Minis Memory" below |
What ships with it
7 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.
- 1mo ago First seen · 347 lines · 83 tokens per session scan A 25ff48212c45
self-improving-agent is a skill published in the GitHub repository OpenMinis/MinisSkills (502 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 3,450 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.