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 vnbochkarev-netizen/ViBo-memory --skill vibo-selfdeedgit clone --depth 1 https://github.com/vnbochkarev-netizen/ViBo-memoryWrote 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/vnbochkarev-netizen/vibo-memory/vibo-selfdeed)<a href="https://agentmods.dev/skills/vnbochkarev-netizen/vibo-memory/vibo-selfdeed"><img src="https://agentmods.dev/badge/skills/vnbochkarev-netizen/vibo-memory/vibo-selfdeed/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/vnbochkarev-netizen/vibo-memory/vibo-selfdeed"><img src="https://agentmods.dev/badge/skills/vnbochkarev-netizen/vibo-memory/vibo-selfdeed.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 | $0.00080 | $0.02652 |
| Opus 5 | $0.00040 | $0.01326 |
| Sonnet 5 | $0.00016 | $0.00530 |
| Haiku 4.5 | $0.00008 | $0.00265 |
Grade A, and why
vibo-selfdeed 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibo-selfdeed — Self-Improving Agent Mission Skill
A task-style skill: the agent receives ONE concrete multi-step task and executes it as an autonomous mission, using ViBo Memory as the brain (context, past lessons, linked facts).
The more the agent works — the more it remembers — the better it does next time.
When to use
Trigger: ONLY when the user explicitly hands the agent a multi-step task (explicit delegation). The skill never auto-triggers on similar-looking tasks, search requests, or routine edits:
- "Find and fix errors in project X" (code)
- "Proofread and unify documents in folder Y"
- "Check configs for consistency"
- "Find vulnerabilities / mismatches in specs and reports"
The skill defines the execution structure; the concrete task arrives at call time.
Required tools
-
ViBo CLI (
vibo_use.py) — the memory engine. Get it free: https://wwwvibo.com/download/skill (free tier: 500 facts forever, no card required) or a 2-day trial: https://wwwvibo.com/download/trial. SetVIBO_CLI=/path/to/vibo_use.pyif it is not next to the skill. -
vibo_use.py(ViBo CLI) — memory commands -
lib_vibo.py— thin Python client to ViBo (add/find/usage/link/stats) -
safety.py— backups, rollback, attempt/timeout limits -
run_mission.sh— mission wrapper (init/checkpoint/progress/switch/rollback/finish)
🍢 GRILL pre-flight (front door)
Before the mission engine runs, interrogate the intent — the owner's task gets pinned down first:
G1 GROUND — pull context from ViBo
vibo find "<project/task context>"— past decisions, past mistakes, owner rules.- No memory → state that you start from scratch; you WILL create the first record at G5.
G2 GRILL — batches of 3-5 clarifications
- Goal — the WHY: "what should be true when this is done?"
- Risks — what could go wrong / what is fragile.
- Do NOT touch — files, systems, secrets, zones off-limits.
- Success criterion — measurable: "how will we know it worked?"
- Risky task (money/prod/public/destructive) → adversarial round: "what did I miss? worst case?"
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 184 lines · 80 tokens per session scan A 48464d03cb88
vibo-selfdeed is a skill published in the GitHub repository vnbochkarev-netizen/ViBo-memory (1 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 2,652 once invoked, about $0.0004 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
knowledge_store_skill
Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocohealth
Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.
pod-kb
Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.