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 letrplB/second-brain --skill walkgit clone --depth 1 https://github.com/letrplB/second-brainWrote 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/letrplb/second-brain/walk)<a href="https://agentmods.dev/skills/letrplb/second-brain/walk"><img src="https://agentmods.dev/badge/skills/letrplb/second-brain/walk/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/letrplb/second-brain/walk"><img src="https://agentmods.dev/badge/skills/letrplb/second-brain/walk.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 | $0.00022 | $0.03141 |
| Opus 5.5 | $0.00009 | $0.01256 |
| Sonnet 5.5 | $0.00004 | $0.00628 |
| Haiku 4.5 | $0.00002 | $0.00314 |
Grade A, and why
walk 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 1mo 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/walk
Intent. Walk the graph and return what's relevant. Semantic search is the default; topology operations are opt-in via flags.
Modes
Semantic mode (default)
User asks: /walk how does annealing relate to crystallisation in dmsn synthesis?
- Route to
qmdMCP. Uselex(BM25) +vec(semantic) sub-queries. Passintentso qmd's snippets are useful. - Optionally augment with
hyde(hypothetical document) if the query is abstract. - Score and merge results. Filter by
minScore: 0.5to drop low-confidence hits. - Return a ranked list:
[[claim-title-1]] (claim, confidence: probable) description... why-it-matched: ... [[claim-title-2]] ...
Topology mode
Specific operations on the graph structure. Each is a flag; tools/topology.py provides the computation.
| Flag | What it returns |
|---|---|
--orphans |
claims with no inbound or outbound [[wikilinks]] |
--bridges <topic> |
claims with high betweenness centrality bridging the named topic to others |
--neighbors <claim> [--depth N] |
claims within N hops of the named claim |
--centrality |
ranked list of high-centrality (hub) claims |
--moc-coverage |
list of claims that aren't in any _<topic>.md MOC |
--disconnected-clusters [--min-size N] |
pairs of MOCs that share no member claims and no 1-hop cross-edges. Meta-MOCs (frontmatter meta: true) are excluded so they don't pollute the lonely-pair signal. |
Mixed mode
A semantic query with a topology constraint, e.g. /walk crystallisation --neighbors-of dmsn-synthesis --depth 2. Run topology to get a candidate set, then semantic-rank within it.
Behaviour
- Parse the argument: query string, flags.
- Read
vault/vault.yaml. Checkqmd.enabled,surrender.enabled,surrender.walk_integration. Re-read every invocation; never cache any flag. - If topology flag → invoke
tools/topology.pywith the appropriate sub-command. Parse result. - If semantic and
qmd.enabled: true→ invokeqmdsearches. Parse + filter. Continue at step 6. - If semantic and
qmd.enabled: false→ use the grep-fallback path (see "Grep fallback" section below). Continue at step 6. - If topology + semantic → constrain semantic to topology-result subset.
- Format the output as a ranked list with descriptions and a short why-it-matched annotation.
- If
surrender.enabled && surrender.walk_integration: read engagement frontmatter from each result claim, compute decay, render the engagement column and the weakest-grip panel. Else: skip surrender rendering entirely; output is byte-identical to the gated-off behaviour. - Print, with a one-line preamble noting which retrieval path was used (qmd / grep-fallback) and the surrender state (enabled / off).
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.
- 1mo ago First seen · 220 lines · 22 tokens per session scan A 12e505785e79
walk is a skill published in the GitHub repository letrplB/second-brain (1 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 3,141 once invoked, about $0.0001 per session on Opus 5.5. 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
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…
pages
Browse, open, or print distilled pages, reusing the wenlan pages CLI for the actual open (one implementation on your PATH, no setup). /wenlan pages opens the page when one matches, or shows a small native picker when 2-4 match. /wenlan pages --print reads the page here instead of opening an editor. /wenlan pages lists…
forget
Delete a memory from Wenlan by ID. Destructive and cannot be undone — prefer /capture with supersedes for corrections. Invoked as /wenlan forget .
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
raytsystem-save
Stage a cited synthesis as a typed raytsystem DRAFT bundle and escaped preview. Use for SAVE, preserving a verified query answer, preparing a knowledge proposal, or creating a reviewable draft; never treat SAVE as canonical promotion or publication.