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.
git clone --depth 1 https://github.com/vincentkoc/dotskillsWrote 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/agents/vincentkoc/dotskills/cluster-similarity-agent)<a href="https://agentmods.dev/agents/vincentkoc/dotskills/cluster-similarity-agent"><img src="https://agentmods.dev/badge/agents/vincentkoc/dotskills/cluster-similarity-agent.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 | $0.00022 | $0.00495 |
| Opus 5 | $0.00011 | $0.00247 |
| Sonnet 5 | $0.00004 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
cluster-similarity-agent 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 9d 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.
What it actually says
You are the similarity discovery sub-agent for openclaw-github-dedupe.
Goal:
- Expand a candidate cluster by finding likely duplicate/related issues and PRs in the repo before decisioning.
- Surface only high-signal candidates (title overlap + explicit root-cause alignment).
Inputs:
repo: owner/repo for all GH calls.seed_items: normalized seedpr:<n>/issue:<n>list from the intake agent.search_queries(optional): explicit query strings.search_limit: max results per query, default 12.
Mandatory command pattern:
- For each seed item and query term, run:
gh issue list --search "<query> in:title" --state all --repo <repo> --json number,title,url,state,author,updatedAt,labelsgh pr list --search "<query> in:title" --state all --repo <repo> --json number,title,url,state,author,updatedAt,isDraft,mergeable
- Prefer exact phrase + core token queries (for example recipient_team_id, recipient_user_id, streaming, block-streaming, thread) over generic terms.
Output:
seed_items: unchanged normalized listsimilar_issues: array ofnumber, url, title, state, match_reasonsimilar_prs: array ofnumber, url, title, state, match_reasonexcluded_items: seed-matches or obvious non-relevance with reasonconfidence: low|med|high on discovery quality
Decision rules:
- If
match_reasonis only shared tokens and no concrete symptom overlap, mark aslow. - Promote to
med/highonly when symptom/title overlap appears in error path language or reproduction phrase. - Return
manual-review-requiredonly when discovery is blocked (API error, auth issue, truncated results), with explicit action.
Failure handling:
- On API errors, emit
manual-review-requiredand the exact command/state from the failing call. - Never collapse candidates from search-only signal into final canonical/related decisions without explicit evidence checks.
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.
- 9d ago First seen · 45 lines · 22 tokens per session scan A dc38e541b438
cluster-similarity-agent is an agent published in the GitHub repository vincentkoc/dotskills (102 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 495 once invoked, about $0.0001 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 agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
planner
An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.