Self Improving Agent

What it does

When your agent uses it

• Skill completion/error with hooks-based self-correction

Example prompts

• “/self-improving-agent”

Requirements

• A Bash shell
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob, WebSearch

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Semantic Memory (memory/semantic-patterns.json)
2. 2Episodic Memory (memory/episodic/)
3. 3Working Memory (memory/working/)
4. 4Experience Extraction
5. 5Pattern Abstraction
6. 6Skill Updates

What it can do on your machine

Read from SKILL.md and the folder at commit 2000ef8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash
  • Grep
  • Glob
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Shell), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • arxiv.org
  • dl.acm.org
  • shothota.medium.com
  • medium.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Self Improving Agent loads about 3.3k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 583 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~67

When it runs · the whole SKILL.md, loaded when a task matches

~3.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from farm-fe/farm at commit 2000ef8, republished under its MIT licence (© farm-fe). 583 words, ~3,311 tokens.

name

self-improving-agent

description

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.

allowed-tools

Read, Write, Edit, Bash, Grep, Glob, WebSearch

┌─────────────────────────────────────────────────────────────────┐
│                    UNIVERSAL SELF-IMPROVEMENT                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   Skill Event → Extract Experience → Abstract Pattern → Update  │
│        │                  │                │         │          │
│        ▼                  ▼                ▼         ▼          │
│   ┌─────────────────────────────────────────────────────┐       │
│   │              MULTI-MEMORY SYSTEM                      │       │
│   ├─────────────────────────────────────────────────────┤       │
│   │  Semantic Memory   │  Episodic Memory  │ Working Memory │  │
│   │  (Patterns/Rules)  │  (Experiences)    │  (Current)     │  │
│   │  memory/semantic/  │  memory/episodic/ │  memory/working/│  │
│   └─────────────────────────────────────────────────────┘       │
│                                                                 │
│   ┌─────────────────────────────────────────────────────┐       │
│   │              FEEDBACK LOOP                            │       │
│   │  User Feedback → Confidence Update → Pattern Adapt   │       │
│   └─────────────────────────────────────────────────────┘       │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

{
  "patterns": {
    "pattern_id": {
      "id": "pat-2025-01-11-001",
      "name": "Pattern Name",
      "source": "user_feedback|implementation_review|retrospective",
      "confidence": 0.95,
      "applications": 5,
      "created": "2025-01-11",
      "category": "prd_structure|react_patterns|async_patterns|...",
      "pattern": "One-line summary",
      "problem": "What problem does this solve?",
      "solution": { ... },
      "quality_rules": [ ... ],
      "target_skills": [ ... ]
    }
  }
}

memory/episodic/
├── 2025/
│   ├── 2025-01-11-prd-creation.json
│   ├── 2025-01-11-debug-session.json
│   └── 2025-01-12-refactoring.json

{
  "id": "ep-2025-01-11-001",
  "timestamp": "2025-01-11T10:30:00Z",
  "skill": "debugger",
  "situation": "User reported data not refreshing after form submission",
  "root_cause": "Empty callback in onRefresh prop",
  "solution": "Implement actual refresh logic in callback",
  "lesson": "Always verify callbacks are not empty functions",
  "related_pattern": "callback_verification",
  "user_feedback": {
    "rating": 8,
    "comments": "This was exactly the issue"
  }
}

memory/working/
├── current_session.json   # Active session data
├── last_error.json        # Error context for self-correction
└── session_end.json       # Session end marker

What happened:
  skill_used: {which skill}
  task: {what was being done}
  outcome: {success|partial|failure}

Key Insights:
  what_went_well: [what worked]
  what_went_wrong: [what didn't work]
  root_cause: {underlying issue if applicable}

User Feedback:
  rating: {1-10 if provided}
  comments: {specific feedback}

If experience_repeats 3+ times:
  pattern_level: critical
  action: Add to skill's "Critical Mistakes" section

If solution_was_effective:
  pattern_level: best_practice
  action: Add to skill's "Best Practices" section

If user_rating >= 7:
  pattern_level: strength
  action: Reinforce this approach

If user_rating <= 4:
  pattern_level: weakness
  action: Add to "What to Avoid" section

<!-- Evolution: 2025-01-12 | source: ep-2025-01-12-001 | skill: debugger -->

## Pattern Added (2025-01-12)

**Pattern**: Always verify callbacks are not empty functions

**Source**: Episode ep-2025-01-12-001

**Confidence**: 0.95

### Updated Checklist
- [ ] Verify all callbacks have implementations
- [ ] Test callback execution paths

<!-- Correction: 2025-01-12 | was: "Use callback chain" | reason: caused stale refresh -->

## Corrected Guidance

Use direct state monitoring instead of callback chains:
```typescript
// ✅ Do: Direct state monitoring
const prevPendingCount = usePrevious(pendingCount);

### Phase 4: Memory Consolidation

1. **Update semantic memory** (`memory/semantic-patterns.json`)
2. **Store episodic memory** (`memory/episodic/YYYY-MM-DD-{skill}.json`)
3. **Update pattern confidence** based on applications/feedback
4. **Prune outdated patterns** (low confidence, no recent applications)

## Self-Correction (on_error hook)

Triggered when:
- Bash command returns non-zero exit code
- Tests fail after following skill guidance
- User reports the guidance produced incorrect results

**Process:**

```markdown
## Self-Correction Workflow

1. Detect Error
   - Capture error context from working/last_error.json
   - Identify which skill guidance was followed

2. Verify Root Cause
   - Was the skill guidance incorrect?
   - Was the guidance misinterpreted?
   - Was the guidance incomplete?

3. Apply Correction
   - Update skill file with corrected guidance
   - Add correction marker with reason
   - Update related patterns in semantic memory

4. Validate Fix
   - Test the corrected guidance
   - Ask user to verify

<!-- Correction: 2025-01-12 | was: "useMemo for claimable ids" | reason: stale data at click time -->

## Self-Correction: Click-Time Computation

**Issue**: Using useMemo for claimable IDs caused stale data
**Fix**: Compute at click time for always-fresh data
**Pattern**: click_time_vs_open_time_computation

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash|Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "bash ${SKILLS_DIR}/self-improving-agent/hooks/pre-tool.sh \"$TOOL_NAME\" \"$TOOL_INPUT\""
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash ${SKILLS_DIR}/self-improving-agent/hooks/post-bash.sh \"$TOOL_OUTPUT\" \"$EXIT_CODE\""
          }
        ]
      }
    ],
    "Stop": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "bash ${SKILLS_DIR}/self-improving-agent/hooks/session-end.sh"
          }
        ]
      }
    ]
  }
}

© farm-fe, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in .agents/skills/self-improving-agent of farm-fe/farm.

• SKILL.md
• README.md
• hooks/post-bash.sh
• hooks/pre-tool.sh
• hooks/session-end.sh
• memory/semantic-patterns.json
• references/appendix.md
• templates/correction-template.md
• templates/pattern-template.md
• templates/validation-template.md

Open the folder on GitHubat commit 2000ef8

Used in 2 other repositories

We found 10 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in farm-fe/farm, which our catalogue first saw on October 7, 2026.

• 1mancompany/OneManCompanysrc/onemancompany/default_skills/self-improving-agentcompany/human_resource/employees/00002/skills/self-improving-agent+6 more
• aiskillstore/marketplaceskills/charon-fan/self-improving-agent