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 DavidROliverBA/ArchitectKB --skill auto-summarygit clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBWrote 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/davidroliverba/architectkb/auto-summary)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/auto-summary"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/auto-summary.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 5.1 | $0.00010 | $0.01146 |
| Opus 5 | $0.00005 | $0.00573 |
| Sonnet 5 | $0.00002 | $0.00229 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
auto-summary 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 7d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-summary
Batch populate the summary frontmatter field on notes where it is null or missing. The summary field is the highest-value AI triage field — it enables fast note discovery without reading full content.
Usage
/auto-summary # Process all notes with null summary
/auto-summary <path> # Process specific file or folder
/auto-summary --dry-run # Preview summaries without applying
/auto-summary --type Concept # Only process specific note type
/auto-summary --limit 50 # Process at most 50 notes
Instructions
Phase 1: Find Notes Needing Summary
Use Grep to find notes with null or missing summary:
# Find notes with summary: null
Grep for "summary: null" in *.md files
# Also find notes with no summary field at all
# (These should have had summary added by template cleanup)
Filter results:
- Exclude
Templates/,.obsidian/,.claude/,Archive/,Attachments/ - Exclude Daily notes (journals don't need summaries)
- If
--typespecified, filter by frontmatter type - Sort by type for batch efficiency
Phase 2: Generate Summaries (Parallel)
Launch parallel Haiku sub-agents, batching 20 notes per agent:
For each note, the agent should:
- Read the full note (frontmatter + body)
- Generate a one-line summary following these rules:
Summary Writing Rules
- Length: 10-25 words. One sentence. No period at the end
- Voice: Active, descriptive. State what the note IS or DOES
- Content: Capture the core purpose, not details
- Avoid: Starting with "This note...", "A document about...", "Summary of..."
- Include: Key entities, technologies, or decisions where relevant
Summary Patterns by Type
| Type | Pattern | Example |
|---|---|---|
| Concept | What X is | Continuous Airworthiness Management Organisation responsible for aircraft safety compliance |
| Pattern | How to do X | Event-driven architecture pattern using Kafka for real-time system integration |
| Meeting | What was discussed/decided | Alpha sprint review covering data migration progress and API blockers |
| ADR | What was decided and why | Selected AWS Bedrock over Azure OpenAI for AlertHub safety processing |
| Project | What the project delivers | SAP to DataPlatform data integration enabling unified engineering analytics |
| System | What the system does | MRO Vendor MRO platform managing aircraft maintenance scheduling |
| Person | Role and context | Solutions Architect in Engineering IT, Alpha project lead |
| Task | What needs to be done | Implement Kafka consumer for Alpha work order events |
| Incubator | What idea is being explored | Exploring voice-activated Claude Code workflows for hands-free note capture |
| Research | What question was investigated | Analysis of vault structure identifying efficiency improvements for human and AI workflows |
| Reference | What the resource covers/teaches | AWS documentation on Bedrock guardrails for AI model safety |
| What the email communicates | Proposal to Beta programme board for Claude Code adoption across architecture team |
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.
- 7d ago First seen · 140 lines · 10 tokens per session scan A db7e51d24c3c
auto-summary is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,146 once invoked, about $0.0001 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
x-tweet-by-conversation
Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
auditing-azure-active-directory-configuration
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.