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 dungnotnull/hybrid-harness-chaos-process-prm --skill s02-taste-memorygit clone --depth 1 https://github.com/dungnotnull/hybrid-harness-chaos-process-prmWrote 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/dungnotnull/hybrid-harness-chaos-process-prm/s02-taste-memory)<a href="https://agentmods.dev/skills/dungnotnull/hybrid-harness-chaos-process-prm/s02-taste-memory"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s02-taste-memory/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/dungnotnull/hybrid-harness-chaos-process-prm/s02-taste-memory"><img src="https://agentmods.dev/badge/skills/dungnotnull/hybrid-harness-chaos-process-prm/s02-taste-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00109 | $0.03073 |
| Opus 5 | $0.00055 | $0.01537 |
| Sonnet 5 | $0.00022 | $0.00615 |
| Haiku 4.5 | $0.00011 | $0.00307 |
Grade A, and why
taste-memory-management 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 11d 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste & Memory Management (s02)
Purpose
Build and maintain a persistent model of the developer's preferences across all interactions — technology choices, code style, naming conventions, workflow habits, approval thresholds, and risk tolerance. Ensure every AI agent in this project has access to this preference model so they don't repeat mistakes or violate established conventions.
Prerequisites
- At least one skill execution completed (taste is learned from interaction)
- .commandcode/taste/ directory exists (created automatically if absent)
- No prerequisites required for first-time initialization
Input Contract
| Input | Source | Required |
|---|---|---|
| User corrections / feedback | Real-time user messages | Yes |
| Skill execution history | Progress tracker (s03) | Yes |
| Previous taste file | .commandcode/taste/taste.md |
No (created if absent) |
| CLAUDE.md conventions | Project root | Yes |
Output Contract
| Output | Destination | Format |
|---|---|---|
| Updated taste file | .commandcode/taste/taste.md |
Markdown |
| Taste context object | Injected into all skill contexts | JSON |
| Category-specific taste files | .commandcode/taste/<category>/taste.md |
Markdown |
| Taste summary for new agents | New session bootstrap | Markdown |
Taste Architecture
.commandcode/taste/
├── taste.md # Main file — all categories + learnings
├── pipeline-design/
│ └── taste.md # Moved here when >5 learnings
├── chaos-engineering/
│ └── taste.md
├── governance/
│ └── taste.md
└── ...
Each taste learning follows this format:
## Category Name
- Learning statement with specific guidance. Confidence: 0.XX
Taste Categories
| Category | What It Tracks | Confidence Sources |
|---|---|---|
| Technology | Language, framework, cloud, tool choices | Explicit user statements |
| Code Style | Formatting, naming, patterns, conventions | Corrections to generated code |
| Workflow | Approval gates, skip patterns, phase ordering | Workflow overrides |
| Risk Tolerance | Blast radius limits, chaos intensity, env gates | Chaos-related corrections |
| Communication | Verbosity, format, emoji usage, language | Interaction patterns |
| Testing | Test framework, coverage threshold, approach | Testing-related corrections |
| Deployment | Strategy defaults, rollback behavior | Pipeline-related corrections |
| Observability | Tool preferences, alert thresholds | Monitoring-related corrections |
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.
- 11d ago First seen · 364 lines · 109 tokens per session scan A 28e6671f2210
taste-memory-management is a skill published in the GitHub repository dungnotnull/hybrid-harness-chaos-process-prm (19 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 3,073 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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.