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 AndreVianna/aid-methodology --skill aid-summarizegit clone --depth 1 https://github.com/AndreVianna/aid-methodologyWrote 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/andrevianna/aid-methodology/aid-summarize)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-summarize"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-summarize/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/andrevianna/aid-methodology/aid-summarize"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-summarize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00133 | $0.03763 |
| Opus 5 | $0.00067 | $0.01881 |
| Sonnet 5 | $0.00027 | $0.00753 |
| Haiku 4.5 | $0.00013 | $0.00376 |
Grade A, and why
aid-summarize 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 9d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Visual Summary
State machine: PREFLIGHT -> STALE-CHECK -> PROFILE -> GENERATE -> VALIDATE -> MANUAL-CHECKLIST -> FIX -> APPROVAL -> WRITEBACK -> DONE.
Generates a single self-contained kb.html from a populated and approved
.aid/knowledge/ Knowledge Base. The output is a newcomer-facing product — visually
rich, plain-language, and distinct from the KB itself (which is a dual-audience technical
artifact for humans + AI agents). The KB's authoring rules (no diagrams, tables/bullets)
apply to the KB; they do NOT constrain the summary's format.
The section set is derived data-drivenly from the resolved doc-set
(discovery.doc_set in .aid/settings.yml intersected with docs present on disk),
one section per resolved doc. Each section's attributes (heading, description, component,
tier, keyword pills, cross-links) come from that doc's frontmatter (kb-category,
objective, summary, tags, see_also). Section order is deterministic and
reproducible from the same inputs.
Prerequisite: /aid-discover must have reached DONE and the user must have
approved the KB. This skill does NOT validate KB content — that is discovery's job.
Idempotent: Running /aid-summarize repeatedly on an unchanged KB is a no-op.
It only regenerates the HTML when the KB has been re-reviewed since the last
summarization.
⚠️ Pre-flight Checks
Run .claude/aid/scripts/summarize/summarize-preflight.sh before any state. It verifies:
.aid/knowledge/STATE.mdexists.**User Approved:** yesis present in.aid/knowledge/STATE.md.- At least one populated KB document exists (
.aid/knowledge/*.mdwith real content). - Not in Plan Mode (need write access).
- Node.js >= 22 is available (required for visual-fidelity validation via
validate-visuals.mjs).
If any check fails, the script exits non-zero with a clear actionable message. Do NOT proceed; do NOT create any state files.
Arguments
| Argument | Effect |
|---|---|
--grade X |
Override the minimum acceptable grade. Format: [A-F][-+]?. Without this, runs bash .claude/aid/scripts/config/read-setting.sh --skill summary --key minimum_grade --default A (resolves per-skill override → global review.minimum_grade → default A). When passed, persist to .aid/settings.yml summary.minimum_grade via /aid-config. |
--theme palette=X |
Override color palette (e.g., --theme palette=brand-acme). Default uses the canonical palette in .claude/aid/templates/knowledge-summary/design-tokens.md. |
--reset |
Force regeneration regardless of staleness check; clears ## Knowledge Summary Status in .aid/knowledge/STATE.md. |
What ships with it
10 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.
- references/state-approval.md 2.7 KB
- references/state-done.md 1.1 KB
- references/state-fix.md 3.8 KB
- references/state-generate.md 20 KB
- references/state-manual-checklist.md 3.6 KB
- references/state-preflight.md 1.5 KB
- references/state-profile.md 6.7 KB
- references/state-stale-check.md 1.3 KB
- references/state-validate.md 6.3 KB
- references/state-writeback.md 1.5 KB
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.
- 9d ago First seen · 246 lines · 133 tokens per session scan A d87836d2eaa4
aid-summarize is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 3,763 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 2026-09-03.
Other skills, from other repositories
stage-dsl
The map for reading and editing an OpenMAIC stage document with readstage, patchstage, and grepstage. Load it before patching a structure you have not patched before, when patchstage rejects an operation, or whenever the path from a stage, outline, scene, content object, or action to the field you need is uncertain.…
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
dev-camp-deck
Creates a professional PowerPoint presentation about a Copilot Dev Camp lab or topic. Researches Microsoft Learn documentation, organizes content into a slide structure, and generates a polished deck with speaker notes. Use when user asks to "create a presentation on", "make a deck about", "build a slideshow for"…
read-book
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
training-report
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a…