claude-obsidian is a local knowledge system that turns source material into linked, source-cited Markdown notes in an Obsidian vault for use with Claude Code and compatible agent hosts. People use it to capture research, retrieve evidence-grounded answers, maintain knowledge, and map connections while retaining ownership of their files. The catalogue entries provide workflows and extensions for operating this knowledge system.
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 AgriciDaniel/claude-obsidian --skill wiki-lintgit clone --depth 1 https://github.com/AgriciDaniel/claude-obsidianWrote 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/agricidaniel/claude-obsidian/wiki-lint)<a href="https://agentmods.dev/skills/agricidaniel/claude-obsidian/wiki-lint"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-obsidian/wiki-lint/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/agricidaniel/claude-obsidian/wiki-lint"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-obsidian/wiki-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00079 | $0.00827 |
| Opus 5.5 | $0.00032 | $0.00331 |
| Sonnet 5.5 | $0.00016 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
wiki-lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint the wiki
Use the portable lint engine as the source of truth. Lint observes vault state; it does not create reports, dashboards, canvases, stubs, or fixes.
Resolve the installed product root from this skill's own location, not from the vault or current working directory:
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"
Every ../wiki/references/ link in this file resolves the same way, relative
to this skill's own directory under $PRODUCT_ROOT, never relative to the
selected vault's wiki/ directory.
Run
Resolve the user vault, then run one of:
python3 "$CORE" lint --vault "$VAULT"
python3 "$CORE" lint --vault "$VAULT" --format markdown
python3 "$CORE" lint --vault "$VAULT" --exclude "wiki/scratchpad/*"
The repeatable --exclude GLOB flag scopes a path (for example a scratchpad
folder) out of page, link-resolution, orphan, frontmatter, empty-section, and
stale-index scanning.
Use --strict only when a nonzero exit for findings is useful in automation.
The command remains read-only either way.
The deterministic parser understands Obsidian wikilinks and embeds, Markdown
links, aliases, heading and block fragments, escaped aliases, and code fences.
It skips dot-prefixed directories by default, mirroring Obsidian's own
indexer. Link resolution honors .gitignore files inside the vault (no git
subprocess): when a link is ambiguous between a page and a gitignored file
such as a build artifact, the gitignored candidate is dropped.
It reports such categories as dead or ambiguous links, orphan pages, required
frontmatter gaps (including title), empty sections, stale index entries, and
source/claim ledger contract violations. Report only the
checks and counts present in its output; do not claim that it performed
semantic, stylistic, or prose-level contradiction analysis when it did
not.
Explain findings
- Preserve the engine's paths, line numbers, targets, categories, and counts.
- Group findings by likely impact: broken navigation, ambiguous resolution, metadata quality, then maintainability.
- Explain that an orphan may be intentional and an ambiguous basename needs a path-qualified link; do not infer intent from the finding alone.
- Treat allowlisted findings as policy, not as proof that the target exists.
- Separate deterministic facts from suggested remediation.
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 Changed · +13 lines a660684a0b1c
- 1mo ago First seen · 74 lines · 79 tokens per session scan A e268098bb634
wiki-lint is a skill published in the GitHub repository AgriciDaniel/claude-obsidian (15,864 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 827 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
share-fix
Turn a fix you made for a whole class of bugs into help for others: reverse-search GitHub for people hitting the same symptom, pick the 3-5 best live threads and post one tailored answer or gist each, no copy-paste fan-out. Use after a verified class fix. Triggers: /share-fix, /sf, share the fix.
five-whys
Investigate the root cause of a recurring or systemic defect across a series of incidents, not a single one. Use on the third recurrence, or when someone asks 'why again?', 'five whys', 'fix the root'. Skip for one or two ordinary cases, an already proven simple cause, or a one-off external outage. Triggers…
tt
Quality gate immediately after building: prove that what was just built actually works, while the context is still hot. Six steps: scope what changed, run live on real data, break it on purpose, show a counter or log proving it ran, root-cause any failure and re-run, then a verdict with evidence. Only a green verdict…
local-chatgpt-token-heal
Re-mint a ChatGPT bearer token when a nightly sync exits with a token-expired code: the session cookie lives for months and deterministically produces a fresh bearer, with no LLM and no browser. Triggers: "/chatgpt-token-heal", "chatgpt token dead", or the sync failing on that error.
tg-check
Self-test both Telegram rails on this machine, the MCP connector and the userbot library, with a deterministic zero-token detector plus a real in-session MCP probe, and print a per-rail verdict with the exact fix for whichever is down. Triggers: "/tg-check", "are both tg rails up", "check telegram channels".
continue
Drive the current task to a verified result instead of stopping at a plausible report. Use when the user says /continue, keep going, not done yet, push further, or is unhappy with the result. Rebuilds requirements from the conversation, re-checks real state, fixes root causes, verifies from the consumer side, offloads…