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 agentmods add skills/ibrain-bvba/gutt-claude-code-plugin/individual-program-designnpx skills add iBrain-BVBA/gutt-claude-code-plugin --skill individual-program-designgit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWrote 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/ibrain-bvba/gutt-claude-code-plugin/individual-program-design)<a href="https://agentmods.dev/skills/ibrain-bvba/gutt-claude-code-plugin/individual-program-design"><img src="https://agentmods.dev/badge/skills/ibrain-bvba/gutt-claude-code-plugin/individual-program-design.svg" alt="Measured on agentmods" 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 | $0.00143 | $0.02557 |
| Opus 5 | $0.00072 | $0.01278 |
| Sonnet 5 | $0.00029 | $0.00511 |
| Haiku 4.5 | $0.00014 | $0.00256 |
Grade A, and why
individual-program-design 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 3d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Individual Program Design
Turn a person's stated goals into a program that survives the session: goals, milestones, a check-in cadence, and the questions still open — written once to their personal memory scope so any later session can reconstruct it without asking them to explain themselves again. Domain-neutral: this shapes the container, never the subject matter.
progress-tracking is the other half — it reads this record back and writes the
check-ins against it. Underneath, memory-capture owns write discipline
(classify, dedup, size caps, write-tool discovery, queued≠persisted),
memory-search owns query phrasing and the relevance gate, and
agent-memory-protocol owns identity for when an agent runs this. Those ship
with the gutt-pro plugin; without it, follow the rules below and note the gap in
one line.
Hard rules (non-negotiable — read first)
- Personal scope, written with
add_personal_memory. That tool takes nogroup_idat all — the namespace is derived server-side from the login and authorized on every call. Without an OAuth login carrying a stable user id the call is denied, not downgraded. Never write a person's program to an org group instead; hand the draft back (see Degradation). Because the namespace comes from the login, it is the authenticated user's own scope — there is no way to write into someone else's. This skill serves whoever is running it, for themselves; run on someone else's behalf it would file their program under your name, so say that rather than doing it. - No agent identity in personal scope. Do not pass
agent_idon a personal read or write. Registration and tagging happen in org scope only, and that isagent-memory-protocol's business. - Privacy runs both ways. Never copy personal-scope content into an
org-scope write or into an org-memory query string. And every org-scope read
issued while program content is in context must pass explicit
group_idsnaming only org groups: omit it and the user's personal scope is already in the default search scope, so private notes leak into what may become a shared briefing. An org write carries nothing personal and passeslast_n_episodes=0(memory-capture). - The goals are the user's. Elicit them; never infer a program and write it. Read the filled-in skeleton back and get an explicit yes first. No confirmation → it stays a draft, and you say so.
- One self-contained program episode,
last_n_episodes=0. The program is the root of the thread and has nothing to chain to, and the server default of3would fold unrelated recent personal episodes into extraction. Use the naming and skeleton below, and do not invent a new typed name prefix — the five (Insight:throughWorkingAgreement:) belong to org captures inmemory-capture. - Never hardcode a tool prefix. The
mcp__…__prefix varies per install, so calladd_personal_memory,get_episodes, etc. by whatever name your tool list actually surfaces — and never assume a write tool's name.
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.
- 3d ago First seen · 192 lines · 143 tokens per session scan A 7e2b724de73b
individual-program-design is a skill published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (5 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 2,557 once invoked, about $0.0007 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
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…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…