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 mehmetdemirci/comb-ai --skill update-memory-bankgit clone --depth 1 https://github.com/mehmetdemirci/comb-aiWrote 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/mehmetdemirci/comb-ai/update-memory-bank)<a href="https://agentmods.dev/skills/mehmetdemirci/comb-ai/update-memory-bank"><img src="https://agentmods.dev/badge/skills/mehmetdemirci/comb-ai/update-memory-bank/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/mehmetdemirci/comb-ai/update-memory-bank"><img src="https://agentmods.dev/badge/skills/mehmetdemirci/comb-ai/update-memory-bank.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 | $0.00036 | $0.00871 |
| Opus 5 | $0.00018 | $0.00436 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
update-memory-bank 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Memory Bank
Update the memory bank to reflect: $ARGUMENTS
Automatic Trigger Conditions
This skill should be invoked automatically when any of these signals are detected:
- Task implementation completed (code changes committed or ready)
- Sprint task marked complete
- Bug fix implemented
- Feature implementation finished
- Architectural decision made
- User says: "done", "finished", "complete", "task completed", "what's next?"
Process
Step 1 — Detect scope
Determine the update scope based on what changed:
| Scope | When | Files to Update |
|---|---|---|
| Minimal | Single task completed | sprint-tracker + active-context |
| Standard | Feature implemented | + progress |
| Full | Sprint completed / major milestone | + archive + arch/tech files |
| Architecture | Architecture decision made | + arch/patterns-overview + arch/decisions-summary |
| Tech Stack | New dependency or technology added | + relevant tech/*.md |
Step 2 — Update files in priority order
Priority 1 — core/sprint-tracker.md
- Mark task as complete with actual hours
- Update sprint completion percentage
- Note any scope changes
Priority 2 — core/active-context.md
- Remove completed items from "current work"
- Add to "last completed" list (keep only 5 most recent)
- Update "next steps" to reflect current state
- Update any resolved blockers
Priority 3 — core/progress.md (standard/full scope only)
- Update "what's working" section
- Update key metrics if changed
- Update overall status
Priority 4 — tech/*.md (if tech stack changed)
- New library added → update tech stack file
- New pattern discovered → add to patterns section
Priority 5 — arch/*.md (if architecture changed)
- New ADR → add to arch/decisions-summary.md
- New pattern → add to arch/patterns-overview.md
Priority 6 — Archive (full scope / sprint boundary only)
- Move completed sprint content from sprint-tracker to progress-archive.md
- Trim progress.md to summary only
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 · 111 lines · 36 tokens per session scan A 19358d7ec4f2
update-memory-bank is a skill published in the GitHub repository mehmetdemirci/comb-ai (13 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 871 once invoked, about $0.0002 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
pneuma-preferences
Persistent user preference memory across sessions. Consult this skill BEFORE making any design, style, or aesthetic decisions — choosing colors, themes, layouts, fonts, tone of voice, content density, or visual direction. Also consult when starting a new creative task in any mode, when the user corrects your style…
context-engineering
Manage what goes into the AI agent context window for maximum quality and minimum waste.
Vibsync setup
Use when installing or connecting the Vibsync MCP server (the shared team brain for AI coding agents), or troubleshooting why Vibsync tools (onboard, recall, remember) aren't available or a connection isn't showing. Covers the one-time browser OAuth connect, team approval, and verifying the first handoff.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies.
rust-project
Modern Rust project architecture guide for 2025. Use when creating Rust projects (CLI, web services, libraries). Covers workspace structure, error handling, async patterns, and idiomatic Rust best practices.