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/skyfox-io/memex/resummarizenpx skills add Skyfox-io/Memex --skill resummarizegit clone --depth 1 https://github.com/Skyfox-io/MemexWrote 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/skyfox-io/memex/resummarize)<a href="https://agentmods.dev/skills/skyfox-io/memex/resummarize"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/resummarize.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 | $0.00050 | $0.01180 |
| Opus 5 | $0.00025 | $0.00590 |
| Sonnet 5 | $0.00010 | $0.00236 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
resummarize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memex - Resummarize
Wikilink rule: When referencing any file in markdown, always use [[filename]] wikilink format.
Refresh manifest and hub summaries to current retrieval-tuned format. The companion to /memex:reindex:
- Resummarize. Rewrites summaries (manifest Hub Map rows, Tier 1 file rows, per-file rows inside each hub).
- Reindex. Rebuilds the per-hub
_CLOSETS.mdtyped-field index.
Run resummarize first on a v1→v2 migration, then reindex. They're independent passes.
Step 0: Detect workspace, acquire lock, detect format version
Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash. Read _MANIFEST.md:
- No
<!-- memex-managedmarker: Tell the user to run/memex:initfirst and stop.
Acquire memory/.resummarize.lock and check the 24-hour cooldown in memory/.resummarize-runs.log. Both follow the shared bulk-write convention. See ../consolidate/references/locking.md.
Look for <!-- summary-format-version:N --> in the manifest:
- Marker says
2and--forcenot passed: ask "Manifest is already v2-format. Resummarize anyway? (y/n)". If no, exit and clear the lock. - Marker says
1or absent: proceed.
Step 1: Identify files to resummarize
Three layers, processed in this order (highest leverage first):
- Tier 1 files in the manifest:
[[CLAUDE]],[[status]],[[session-log]],[[decisions]],[[glossary]],[[ideas]], plus any other Tier 1 entries. - Hub Map rows in the manifest: every
[[*-index]]one-line domain summary. - Hub interiors: every wikilinked entry inside each Tier 2 hub file.
Step 2: Read each file and write a v2 summary
For each file, read its current content and rewrite the summary using the eight v2 summary rules: ../session-end/references/summary-rules.md.
Highlights of the v2 contract (full rules in the reference):
- Enumerate distinct subjects from anywhere in the file, not just opening lines.
- Quote user-stated facts verbatim. Don't paraphrase.
- Name entities by name.
- Cap at 250 characters.
- Capture decision reversals and date/time mentions explicitly.
What ships with it
1 file 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.
- 6d ago First seen · 119 lines · 50 tokens per session scan A be12d9b0c9d9
resummarize is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,180 once invoked, about $0.0003 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
solopreneur-context
When the user wants to set up or update their solopreneur context document — a one-time profile of their business that all other skills reference automatically. Use when the user says "set up my context," "tell you about my business," "save my business info," "update my profile," or when starting a new session and…
obsidian-companion
Use when interacting with the user's Obsidian vault — reading, writing, searching, or chatting with notes using local RAG. Guides tool selection and writing strategy for all vault operations.
wiki-ingest
Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Triggers on "ingest", "process document", "import into vault", "distill this", "add to vault", or "extract knowledge from".
vault-lint
Use when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps. Triggers on "lint vault", "vault health", "check vault", "stale notes", "vault audit", "vault quality", or "check conventions".
compound
Use when the user wants to promote cross-project knowledge to the global Engineering/ folder, or says "promote knowledge", "compound notes", "knowledge synthesis", or "find repeated ideas across projects".
links
Use when the user wants to explore connections between notes, see what links to or from a note, or says "links", "backlinks", "connections", or "graph".