link-retrieve

A small command-line procedure for retrieving relevant project history, source-backed notes, and earlier decisions from Link. It returns bounded context instead of loading the entire stored wiki.

In plain words
What is it for?
Checking Link health, seeding project documentation, searching for relevant context, creating a brief before longer work, and viewing bounded graph summaries or performance results.
Why use it?
It helps the agent use past project knowledge while limiting unrelated information and avoiding unnecessary exposure of sensitive values.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gowtham0992/link/link-retrieve
Any agent
npx skills add gowtham0992/link --skill link-retrieve
Clone the repo
git clone --depth 1 https://github.com/gowtham0992/link

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.00484
Opus 5 $0.00021 $0.00242
Sonnet 5 $0.00008 $0.00097
Haiku 4.5 $0.00004 $0.00048

Measured 3d ago against content hash 890211415998, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

link-retrieve 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 3d 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.

skills/link-retrieve/SKILL.md · 40 lines

What it actually says

Use bounded CLI commands so the agent does not dump the whole wiki into context. Load this skill proactively at the first substantive turn of a session, before project/release/debug/design work, or whenever the answer may depend on prior Link memory. In a source checkout, replace lnk with python3 link.py.

  1. If readiness is unclear, start with:
    lnk health [link-root]
    
  2. If the user is inside a project repo and Link has no project context yet, seed allowlisted source-backed context before broad searching:
    lnk seed . [link-root]
    
    This reads project docs/rule files, blocks secret-looking values, and does not create durable memories.
  3. For most questions, use a compact query packet:
    lnk query "<question or task>" [link-root] --budget micro
    
    Read recall_capsule first. Increase to --budget small, --budget medium, or --budget large only when the packet says more context is needed.
  4. Before longer work, prime from memory:
    lnk brief "<current task>" [link-root]
    
  5. For graph context, stay bounded:
    lnk graph-summary "<topic>" [link-root] --limit 40 --depth 1
    
  6. For performance checks, use:
    lnk benchmark "<topic>" [link-root] --budget small
    

Do not enumerate every page, grep raw files, or request the full graph unless the user explicitly asks for an export or exhaustive audit, or the compact packet is insufficient and tells you which follow-up to use.

Recalled memories carry confidence labels and, when the optional local semantic tier is installed, a match field: lexical, hybrid, or semantic. Treat semantic matches (paraphrase similarity, capped confidence) and weak matches as hints to verify with the user, not facts to act on.

Changes

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.

  1. 3d ago First seen · 40 lines · 42 tokens per session scan A 890211415998

Subscribe to this mod's changes

link-retrieve is a skill published in the GitHub repository gowtham0992/link (180 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 484 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.

Related

Other skills, from other repositories

llm-wiki

Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).

zosmaai/pi-llm-wiki · 52 tokens

youtube-fetcher

Turn a YouTube video into a structured, Obsidian-ready archival Markdown note containing its transcript, creator metadata, description, chapters, language, and capture provenance. Use when a user shares a YouTube URL or video ID and wants transcripts, captions, subtitles, notes, a knowledge-base record, summarization…

JimmySadek/youtube-fetcher-to-markdown · 102 tokens

ingest

Turn messy source notes into structured wiki pages (frontmatter, wikilinks, one folder per type) and update the vault's index, log and hot cache. Use when the user drops files into inbox/ and asks to process them, points at a note or URL to ingest, or pastes raw content to file. Triggers on: "ingest", "ingesta"…

sturlese/hippocampus · 110 tokens

lint

Health check for the vault: runs the deterministic linter (frontmatter, dead links, orphans, duplicates, index drift) plus editorial checks (stale claims, unlinked mentions, missing pages), then fixes what the user approves. Triggers on: "lint", "revisa el vault", "health check", "chequea el wiki", "limpia el vault"…

sturlese/hippocampus · 84 tokens

save

File the current conversation's valuable content (analysis, decision, session summary) as a structured wiki note so it isn't lost in chat history. Triggers on: "save this", "guarda esto", "guárdalo en el wiki", "/save", "$save", "file this", "apunta esto", "guarda esta conversación", "save this session".

sturlese/hippocampus · 78 tokens

obsidian-setup-consultant

Use this skill whenever the user wants to install, configure, migrate, design, or connect Obsidian as a second brain, knowledge base, cloud-synced vault, or AI/Hermes-readable memory. It is especially important when the user asks for an Obsidian setup prompt, vault architecture, folder structure, plugin…

SikJa/hermes-obsidian-setup-consultant · 124 tokens