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 r007b34r/opencode-obsidian-knowledge-workflow --skill connection-reviewgit clone --depth 1 https://github.com/r007b34r/opencode-obsidian-knowledge-workflowWrote 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/r007b34r/opencode-obsidian-knowledge-workflow/connection-review)<a href="https://agentmods.dev/skills/r007b34r/opencode-obsidian-knowledge-workflow/connection-review"><img src="https://agentmods.dev/badge/skills/r007b34r/opencode-obsidian-knowledge-workflow/connection-review/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/r007b34r/opencode-obsidian-knowledge-workflow/connection-review"><img src="https://agentmods.dev/badge/skills/r007b34r/opencode-obsidian-knowledge-workflow/connection-review.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 | $0.00060 | $0.01121 |
| Opus 5.5 | $0.00024 | $0.00448 |
| Sonnet 5.5 | $0.00012 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
connection-review 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 2mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
connection-review
Constraints
- NEVER scan whole vault; scope = 5-15 primary notes + small supporting set
- NEVER treat keyword overlap alone as evidence of connection
- NEVER synthesize week-level meaning (that is weekly-synthesis)
- NEVER write links without explicit user confirmation
- NEVER turn review into whole-vault graphing
Trigger Boundary
Use when: find note connections, suggest wikilinks, identify repeated patterns, surface contradictions, review relationships in a bounded set.
Do NOT use for:
- Raw inbox sorting →
inbox-triage - Week-level thesis and one action →
weekly-synthesis - Vault system health diagnosis →
vault-health-feedback - Upgrading material into stable notes →
note-promotion
Boundaries
- Owns: link discovery, pattern detection, contradiction surfacing, follow-up suggestions
- Delegates to:
note-promotion(follow-up accepted),weekly-synthesis(patterns span week) - Never absorbs: inbox routing, synthesis, health diagnosis, context maintenance
Continuations
| Condition | Next skill |
|---|---|
| Follow-up note suggestion accepted by user | note-promotion |
| Patterns span full week window, user requests synthesis | weekly-synthesis |
| Notes too raw for relationship analysis | inbox-triage |
| All connections weak/uncertain | Escalate to human |
Companion Skill
All vault operations follow obsidian-mcp. Forbidden: obsidian_patch_note, obsidian_append_to_note. Verify every write through readback.
Procedure
Phase 1: Scope
obsidian_list_notesorobsidian_search_notes→ identify recent/specified set- Bound to 5-15 primary notes; reject unbounded requests (ask user to narrow)
Phase 2: Read
- For each:
obsidian_get_note format:"document-map"→ structure overview format:"content"only when evidence is needed for a specific connection- Read older notes only to verify a suspected relationship
Phase 3: Analyze
When analyzing, read references/examples.md for connection quality calibration.
What ships with it
6 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.
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.
- 2mo ago First seen · 122 lines · 60 tokens per session scan A 6a17dacfb269
connection-review is a skill published in the GitHub repository r007b34r/opencode-obsidian-knowledge-workflow (13 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,121 once invoked, about $0.0002 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.
connection-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| connection-reviewr007b34r/opencode-obsidian-knowledge-workflow | Skill | 13 | 6mo ago | Apache-2.0 | A | 60 | Claude Code, Codex |
| projectAlpacaLabsLLC/skills-for-architects | Skill | 421 | 4d ago | MIT | A | 33 | Claude Code |
| llm-wikipraneybehl/llm-wiki-plugin | Skill | 124 | 17d ago | MIT | A | 143 | Claude Code |
| orientharnessprotocol/harness-kit | Skill | 10 | today | Apache-2.0 | A | 80 | Claude Code |
| memoryharnessprotocol/harness-kit | Skill | 10 | today | Apache-2.0 | A | 76 | Claude Code |
| captureharnessprotocol/harness-kit | Skill | 10 | today | Apache-2.0 | A | 73 | Claude Code |
| cc-wikitejpalv/cc-wiki | Skill | 42 | 5mo ago | MIT | A | 76 | Claude Code |