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 strikersam/autonomous-ai-agency --skill learn-rulegit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/learn-rule)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/learn-rule"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/learn-rule/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/strikersam/autonomous-ai-agency/learn-rule"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/learn-rule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Memory Poisoning · line 11 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00038 | $0.00713 |
| Opus 5 | $0.00019 | $0.00357 |
| Sonnet 5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
learn-rule 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: learn-rule
When to Use
Use this skill whenever:
- The user corrects a mistake you made
- You discover a repo-specific rule that isn't in CLAUDE.md
- A pattern works unexpectedly (positively or negatively)
- You want to persist a decision for future sessions
This is how Claude gets smarter at this specific repo over time.
Instructions
Step 1 — Identify the rule
Extract the core rule from the correction or discovery. A good rule is:
- Specific — refers to a concrete situation
- Actionable — tells you what to do or not do
- Memorable — can be read in under 10 seconds
Bad rule: "Be careful with auth code."
Good rule: "Always call risky-module-review before touching admin_auth.py — even for 1-line changes."
Step 2 — Append to learnings file
File: .claude/state/learnings.md
Create it if it doesn't exist. Always append — never overwrite.
## YYYY-MM-DD — <short title>
**Situation:** What was being worked on when this was learned.
**Mistake/Discovery:** What went wrong or what was surprising.
**Rule:** <One clear, actionable sentence starting with a verb.>
**Source:** user-correction | self-discovery | docs
Example entry:
## 2026-04-09 — Don't use git add -A
**Situation:** Committing the router refactor.
**Mistake:** Used `git add -A` which staged keys.json accidentally.
**Rule:** Always stage specific files by name; never use `git add -A` or `git add .`.
**Source:** user-correction
Step 3 — Check if CLAUDE.md should be updated
If the rule is general enough to apply to every future session:
- Read CLAUDE.md
- Add it to the "Coding Rules" section (numbered, concise)
- Use
repo-memory-updaterskill if multiple rules need updating
Learnings File Format
.claude/state/learnings.md:
# Session Learnings
Rules and corrections learned from working in this repo.
Read this at the start of sessions via the `replay-learnings` skill.
---
## YYYY-MM-DD — title
**Situation:** ...
**Mistake/Discovery:** ...
**Rule:** ...
**Source:** ...
---
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.
- 12d ago First seen · 109 lines · 38 tokens per session scan A 1a062b432da8
learn-rule is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 713 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
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
persistent-memory
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
context-management
Project context loading, isolation, and persistent state management across CCPM sessions.
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…