Agent skill

Instinct System

by codewithmukesh in codewithmukesh/dotnet-claude-kit

Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic…

MITAuto-check passed

Install Instinct System

skills CLI
$ npx skills add codewithmukesh/dotnet-claude-kit --skill instinct-system -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install codewithmukesh/dotnet-claude-kit instinct-system --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/codewithmukesh/dotnet-claude-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/instinct-system .claude/skills/instinct-system && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
instinct-system
GitHub stars
751
Token cost
~3.4k tokens
SKILL.md length
954 words
Files
1
Skills in repo
47
Repo updated
First seen
Licence
MIT

At a glance

Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic…

  • Works in 5 steps: Three tiers, one routing decision —… → Instincts are hypotheses, not rules — An… → A user correction is a confirmed… → …
  • SKILL.md covers Core Principles, Patterns, Modes and Anti-patterns, plus 2 more sections
  • Calls just

What it does

Instinct System is an agent skill from codewithmukesh/dotnet-claude-kit. Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic discoveries logged to .claude/learning-log.md. Includes status, export, and import modes. Load this skill when you notice a recurring pattern, a user corrects your output, or you discover something non-obvious. Triggers: "show instincts", "what have you learned", "list instincts", "export instincts", "share instincts"…

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Make Claude Code a .NET 10 Expert. The licence is MIT.

Example prompts

  • “show instincts”
  • “what have you learned”
  • “list instincts”
  • “/instinct-system”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Three tiers, one routing decision — Instincts are unconfirmed hypotheses (.claude/instincts.md). Corrections are user-confirmed rules…
  2. Instincts are hypotheses, not rules — An instinct starts as a guess from a single observation and has no authority until confirmed. "One…
  3. A user correction is a confirmed instinct at full confidence — When the user corrects you, skip the confirmation cycle entirely…
  4. Project-scoped, never global — What holds in one codebase may be wrong in another. Instincts live per-project; transfers between projects…
  5. Review at session start, prune periodically — Read MEMORY.md and load instincts at 0.7+ before writing any code; scan recent log entries…

What it can do on your machine

Read from SKILL.md and the folder at commit 2330089. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • just

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

  • Network

    No URLs in SKILL.md.

    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

Instinct System loads about 3.4k tokens when it runs. Until then it costs about 221 tokens; SKILL.md has 954 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~221
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 codewithmukesh/dotnet-claude-kit at commit 2330089, republished under its MIT licence (© codewithmukesh). 954 words, ~3,369 tokens.

Download SKILL.mdSave it as .claude/skills/instinct-system/SKILL.md (or your agent's skills folder).
name
instinct-system
description
Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic discoveries logged to .claude/learning-log.md. Includes status, export, and import modes. Load this skill when you notice a recurring pattern, a user corrects your output, or you discover something non-obvious. Triggers: "show instincts", "what have you learned", "list instincts", "export instincts", "share instincts", "import instincts", "load instincts from", "learn this", "I think they always", "notice a pattern", "instinct", "hypothesis", "confidence", "learn from mistakes", "remember this", "don't do that again", "log this", "document this finding", "gotcha", "what did we learn", "learnings", "discoveries", or at session start (to load existing knowledge).

Instinct System

One learning system, three tiers. Every signal Claude receives during work — an observed pattern, a user correction, a surprising discovery — routes to exactly one store.

Core Principles

  1. Three tiers, one routing decision — Instincts are unconfirmed hypotheses (.claude/instincts.md). Corrections are user-confirmed rules (MEMORY.md). Discoveries are insights that explain the world (.claude/learning-log.md). Rules prescribe behavior; insights describe it; instincts are rules-in-waiting. Never mix the tiers — a hypothesis in MEMORY.md pollutes permanent knowledge, and a confirmed rule left as an instinct gets forgotten.

  2. Instincts are hypotheses, not rules — An instinct starts as a guess from a single observation and has no authority until confirmed. "One handler uses sealed" is an instinct at 0.3; "all 12 handlers use sealed" is a rule at 0.9. Confidence (0.3–0.9) drives behavior: note at 0.3, mention at 0.5, follow at 0.7, promote at 0.9.

  3. A user correction is a confirmed instinct at full confidence — When the user corrects you, skip the confirmation cycle entirely. Generalize the lesson, capture it immediately in MEMORY.md with the "why", and confirm what was captured. A correction costs the user 30 seconds today and saves hours across all future sessions — losing one is the most expensive mistake this system can make.

  4. Project-scoped, never global — What holds in one codebase may be wrong in another. Instincts live per-project; transfers between projects go through export/import with confidence decay, never at full confidence.

  5. Review at session start, prune periodically — Read MEMORY.md and load instincts at 0.7+ before writing any code; scan recent log entries for the working area. Knowledge captured but never reviewed is wasted effort. Audit all three stores when they bloat — stale instincts, duplicate rules, and unreviewed logs defeat the purpose.

Patterns

Tier Routing
SignalDestinationLifespan
Pattern observed, not yet confirmed ("I think they always...").claude/instincts.md at 0.3Until promoted or discarded
User correction ("no, use X", "don't do that again", "remember this")MEMORY.md immediately, generalizedPermanent until proven wrong
Instinct reaching 0.9 confidencePromote to MEMORY.md, remove from instinctsPermanent
Non-obvious discovery (bug root cause, gotcha, workaround, perf finding).claude/learning-log.md3–6 months, then archive or promote
Same gotcha logged 3+ timesPromote to MEMORY.md as a preventive rulePermanent
Session state (done/pending)Handoff via wrap-up — not this systemUntil next session
Instinct Lifecycle (Observe-Hypothesize-Confirm)
1. OBSERVE     — "This handler is internal sealed class. Convention?"
2. HYPOTHESIZE — Write to .claude/instincts.md at confidence 0.3:
                 - Use `sealed` on handler classes | confidence: 0.3 | seen: 1 | last: 2026-06-12
3. SEEK        — Actively check 2-3 related files (find_symbol, get_public_api).
                 Passive observation is not enough.
4. ADJUST      — Confirmed: raise per the adjustment track.
                 Contradicted: halve confidence, note the exception.
                 Mixed: hold steady, note the split.
5. PROMOTE     — At 0.9, present evidence and offer promotion to MEMORY.md.
Instinct Storage Format

.claude/instincts.md, grouped by category with structured metadata:

markdown
# Project Instincts

## Code Style [0.7]
- Use `sealed` on all handler classes | confidence: 0.8 | seen: 5 | last: 2026-06-12
- Prefix private fields with underscore | confidence: 0.5 | seen: 2 | last: 2026-06-10

## Architecture [0.7]
- Feature folders use singular names | confidence: 0.7 | seen: 4 | last: 2026-06-12

Category header [0.7] = average confidence. Standard categories: Code Style, Architecture, Naming, Testing, Data Access, API Design, Configuration, Performance, Tooling.

Confidence Adjustment Rules

No ad-hoc scoring. Follow this track precisely:

CONFIRMATION:  1st observation → 0.3 | 2nd → 0.5 | 3rd → 0.7 | 4th → 0.8
               5th+ with zero contradictions → 0.9 (promotion candidate)

CONTRADICTION: Any contradiction → halve current confidence (0.7 → 0.35)
               Two in a row → 0.1 (effectively dead)

USER OVERRIDE: Explicit confirm → 0.8 | Explicit correct → 0.0 (remove,
               capture in MEMORY.md instead) | "Sometimes" → cap at 0.5

STALENESS:     No observations for 10+ sessions → flag for review
               Contradicted, unreconfirmed for 5 sessions → remove
Acting on Instincts by Confidence
0.0–0.2 → IGNORE  — insufficient evidence, do not mention
0.3–0.4 → NOTE    — record internally, do not apply
0.5–0.6 → MENTION — "This project may use [pattern]. Follow it?"
0.7–0.8 → FOLLOW  — apply by default, mention on first use
0.9     → PROMOTE — offer to add to MEMORY.md as a permanent rule

Never silently apply an instinct below 0.7.

Correction Capture Flow (Tier 2)

When the user corrects your output ("no, use X instead", "we don't do it that way", "always/never do X", "remember this"):

1. DETECT      — Recognize the correction signal.
2. ACKNOWLEDGE — "Got it — HybridCache instead of IMemoryCache."
3. GENERALIZE  — Specific: "Don't use IMemoryCache in the Orders endpoint"
                 General:  "Always use HybridCache over IMemoryCache —
                            stampede protection + L1/L2 out of the box."
                 Ask: is this specific to this file? This layer? What's the
                 underlying principle? Store the broadest correct statement.
4. CHECK       — Scan MEMORY.md for overlap. Update an existing rule rather
                 than adding a near-duplicate.
5. STORE       — Write under the right category, one line, rationale after
                 the dash. If a matching instinct exists, remove it — it
                 just graduated.
6. CONFIRM     — "Added to Memory > Data Access: HybridCache over IMemoryCache."

MEMORY.md format — same categories as instincts, one actionable rule per line:

markdown
## Data Access
- Always use HybridCache over IMemoryCache — stampede protection + L1/L2
- Never use repository pattern over EF Core — use DbContext directly
Discovery Logging (Tier 3)

Log organic findings to .claude/learning-log.md the moment they occur — a 2-line entry written immediately beats a paragraph reconstructed later. Entry format:

markdown
## 2026-06-12 | Gotcha | MassTransit Consumer Registration Order Matters
Multiple consumers for one message type run in registration order; if the
first throws, the rest are skipped. Caused missed audit events.
**Files:** `src/Shared/Extensions/MassTransitConfig.cs:15-30`
**Resolution:** Independent consumer endpoints or the retry filter.

Log when (and only when) you hit one of these triggers:

Bug Root Cause        — the cause was NOT where the error appeared
Architecture Decision — discovered WHY something is built a certain way
Gotcha                — framework/library behaved surprisingly
Performance Discovery — unexpected perf behavior, with the measurement
Pattern Found         — reusable codebase pattern worth remembering
External Service      — third-party API behaves differently than documented

Those six trigger names are also the category vocabulary — use them verbatim in entries. Routine changes with nothing surprising do not get logged.

Session-Start Loading
1. Read MEMORY.md — apply rules proactively, don't wait to be reminded
2. Read .claude/instincts.md — load 0.7+ as defaults, note 0.5–0.6
3. Scan recent learning-log entries for the area you're working in
4. Flag stale instincts (10+ sessions without observation) for review

Modes

Three operations on the instinct store, invoked by name or trigger phrase.

Status ("show instincts", "what have you learned", "list instincts")
  1. Read .claude/instincts.md; parse each entry's metadata.
  2. Sort by confidence descending, group by category, render as a table: instinct | confidence | category | status (new / stable / reinforced / decaying / promotion candidate).
  3. Summarize health: total count, average confidence, recently reinforced vs decaying entries, any conflicting instincts.
Show full SKILL.md (360 more words)Show less
Export ("export instincts", "share instincts")
  1. Read .claude/instincts.md; filter to confidence > 0.7 (threshold configurable).
  2. Strip project-specific context (file paths, line numbers) while preserving the pattern itself.
  3. Write to .claude/instincts-export.md with portable metadata.
  4. Report what was exported and what was skipped (below threshold), with the output path.
Import ("import instincts", "load instincts from")
  1. Read the export file (user-provided path or .claude/instincts-export.md) and the current .claude/instincts.md.
  2. Merge each imported instinct:
    • No local match — add with confidence decayed by 0.2 (0.9 → 0.7); never import above 0.7. Mark source: imported from [project].
    • Matching instinct exists — keep the higher confidence, mark reinforced.
    • Conflicting instinct exists — present both to the user for resolution; do not auto-overwrite local evidence.
  3. Write the merged result and report imported / merged / conflicts. Every project must confirm imported patterns locally.

Anti-patterns

Over-Eager Pattern Recognition
# BAD — first observation treated as a rule
*Reads one handler* "This project always uses internal sealed class."
*Generates 5 handlers that contradict 8 of 9 existing ones*

# GOOD — hypothesis at 0.3, then active confirmation
"Noticed internal sealed in CreateOrderHandler. Instinct at 0.3.
 Checking 3 more handlers..." *All public* → "Disconfirmed. Discarding."
Fixing Without Capturing
# BAD — correction applied, lesson lost
User: "No, we use HybridCache here"
Claude: "Fixed." *Next session: same mistake*

# GOOD — fix AND capture
Claude: "Fixed. Added to Memory > Data Access:
         Always use HybridCache over IMemoryCache."
Logging Everything
# BAD — noise entry
## 2026-06-12 | Pattern Found | Used Primary Constructors

# GOOD — only the non-obvious earns an entry
## 2026-06-12 | Gotcha | Primary Constructor Params Captured as Fields
Declaring an explicit field with the same name warns but compiles —
and the two can silently diverge.
Write-Only Stores
# BAD — 40 instincts at 0.3 from 3 months ago; MEMORY.md at 200 lines
  with duplicates; 500-line log nobody reads
# GOOD — periodic audit: remove instincts below 0.2 or stale 10+
  sessions; merge/prune MEMORY.md past 50 rules; every ~20 log entries,
  promote recurring findings and archive the stale. Keep instincts
  under 50 active entries.

Decision Guide

ScenarioAction
First time seeing a patternInstinct at 0.3, check 2-3 related files
Pattern seen 3+ times, no contradictionsRaise to 0.7, follow by default
Pattern contradictedHalve confidence, note the exception
User says "we always do X"Instinct at 0.8 (user confirmation)
User corrects your codeGeneralize → MEMORY.md immediately; drop any matching instinct
User says "remember this" / "always/never"Capture in MEMORY.md as stated, generalized
Same correction given twiceHigh priority — the rule wasn't captured or reviewed
Correction about a one-time taskDon't store — only reusable patterns
User asks to forget a ruleRemove from MEMORY.md immediately
Non-obvious bug, gotcha, workaround, perf surpriseLog to learning-log with category + files
Same gotcha logged 3+ timesPromote to MEMORY.md as a preventive rule
Instinct at 0.9Present evidence, offer promotion to MEMORY.md
User partially confirms ("only for commands")Narrow scope, reset to 0.5, re-confirm
Sharing patterns with another projectExport at 0.7+, import with 0.2 decay
Conflict during importPresent both to the user; never auto-overwrite
Any store bloats (50+ entries/rules)Audit: prune dead, merge duplicates, promote mature
Starting a sessionLoad MEMORY.md, instincts 0.7+, recent log entries
  • convention-learner — detects codebase conventions in bulk; feed its findings in as instincts
  • wrap-up — end-of-session ritual; routes session learnings into the correct tier of this system

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

Files

Just SKILL.md in skills/instinct-system of codewithmukesh/dotnet-claude-kit.

Open the folder on GitHubat commit 2330089

Compare with similar skills

Instinct System next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Instinct System compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Instinct System this skillcodewithmukesh/dotnet-claude-kit751—~3.4kAutomated safety check: PassMIT
Langsmith ObservabilityOrchestra-Research/AI-Research-SKILLs13k3 repos~2.4kAutomated safety check: PassMIT
Frontend Observabilitysickn33/agentic-awesome-skills47k1 repos~5.1kAutomated safety check: PassMIT
Ebpf Observabilitysickn33/agentic-awesome-skills47k2 repos~3.3kAutomated safety check: NotesMIT
Python Observabilitywshobson/agents40k—~1.8kAutomated safety check: PassMIT
Observability Designeralirezarezvani/claude-skills28k—~3.5kAutomated safety check: PassMIT

Similar skills

  • Langsmith Observability

    Orchestra-Research/AI-Research-SKILLs

    LLM observability platform for tracing, evaluation, and monitoring.

    13k GitHub starsUsed in 3 repos~2.4k tokens
    AI & LLM EngineeringAuto-check passed
  • Frontend Observability

    sickn33/agentic-awesome-skills

    A portable, framework-agnostic field-side observability system for any React or React Native app.

    47k GitHub starsUsed in 1 repo~5.1k tokens
    DevOps & CloudAuto-check passed
  • Ebpf Observability

    sickn33/agentic-awesome-skills

    Use eBPF for deep kernel-level observability — trace syscalls, network flows, and application behavior without code changes using Cilium, Tetragon, and bpftrace.

    47k GitHub starsUsed in 2 repos~3.3k tokens
    DevOps & CloudAuto-check: notes
  • Python Observability

    wshobson/agents

    Python observability patterns including structured logging, metrics, and distributed tracing.

    40k GitHub stars~1.8k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed
  • Observability Designer

    alirezarezvani/claude-skills

    Design production-ready observability strategies combining metrics, logs, and traces.

    28k GitHub stars~3.5k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Observability Triage

    every-app/open-seo

    Triage OpenSEO production errors in Cloudflare Workers Observability — verified query recipes, counting gotchas, and a known-noise filter list applied automatically.

    23k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed

More from codewithmukesh/dotnet-claude-kit

All 47 skills in this repo
  • API Versioning

    codewithmukesh/dotnet-claude-kit

    API versioning strategies for ASP.NET Core. An agent skill from codewithmukesh/dotnet-claude-kit.

    751 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Scaffold

    codewithmukesh/dotnet-claude-kit

    Architecture-aware feature scaffolding for .NET 10 projects.

    751 GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Architecture Advisor

    codewithmukesh/dotnet-claude-kit

    Architecture selection advisor for .NET applications. An agent skill from codewithmukesh/dotnet-claude-kit.

    751 GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed
  • Aspire

    codewithmukesh/dotnet-claude-kit

    .NET Aspire for cloud-native orchestration. An agent skill from codewithmukesh/dotnet-claude-kit.

    751 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Authentication

    codewithmukesh/dotnet-claude-kit

    Authentication and authorization for ASP.NET Core. An agent skill from codewithmukesh/dotnet-claude-kit.

    751 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Caching

    codewithmukesh/dotnet-claude-kit

    Caching strategies for .NET 10 applications. An agent skill from codewithmukesh/dotnet-claude-kit.

    751 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed

Questions about Instinct System

What does Instinct System do?

Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic…. Instinct System is an agent skill from codewithmukesh/dotnet-claude-kit.md.

How do I install Instinct System in Claude Code?

Run `npx skills add codewithmukesh/dotnet-claude-kit --skill instinct-system -a claude-code`. Or copy the skill folder (skills/instinct-system in codewithmukesh/dotnet-claude-kit) into .claude/skills/instinct-system in your project. Claude Code loads it when a task matches its description.

How do I install Instinct System in Codex?

Run `npx skills add codewithmukesh/dotnet-claude-kit --skill instinct-system -a codex`. Or copy the skill folder (skills/instinct-system in codewithmukesh/dotnet-claude-kit) into .agents/skills/instinct-system in your project. Codex loads it when a task matches its description.

Can I use Instinct System in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add codewithmukesh/dotnet-claude-kit --skill instinct-system -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/instinct-system, .gemini/skills/instinct-system, .github/skills/instinct-system and .opencode/skills/instinct-system in your project.

What does Instinct System need to run?

Going by SKILL.md and its folder, Instinct System needs the command-line tools its instructions call (just).

Does Instinct System access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Instinct System safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Instinct System use?

Instinct System is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Instinct System use?

About 3.4k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Instinct System?

Skills that share tags, products or a category with Instinct System: Langsmith Observability (Orchestra-Research/AI-Research-SKILLs, 13k stars), Frontend Observability (sickn33/agentic-awesome-skills, 47k stars), Ebpf Observability (sickn33/agentic-awesome-skills, 47k stars) and Python Observability (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Instinct System?

codewithmukesh (a GitHub organization) maintains it in codewithmukesh/dotnet-claude-kit, which has 751 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on August 7, 2026.

Source: codewithmukesh/dotnet-claude-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.