Borrowing it
Nothing to install: this file belongs to warpdotdev/oz-for-oss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/warpdotdev/oz-for-oss/main/.agents/skills/update-dedupe/SKILL.mdgit clone --depth 1 https://github.com/warpdotdev/oz-for-ossWrote 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/warpdotdev/oz-for-oss/update-dedupe)<a href="https://agentmods.dev/skills/warpdotdev/oz-for-oss/update-dedupe"><img src="https://agentmods.dev/badge/skills/warpdotdev/oz-for-oss/update-dedupe/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/warpdotdev/oz-for-oss/update-dedupe"><img src="https://agentmods.dev/badge/skills/warpdotdev/oz-for-oss/update-dedupe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 52 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 20 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 21 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00049 | $0.00817 |
| Opus 5.5 | $0.00020 | $0.00327 |
| Sonnet 5.5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
update-dedupe 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Dedupe
Use this skill to improve .agents/skills/dedupe-issue-local/SKILL.md from real closed-as-duplicate signals. The core skill at .agents/skills/dedupe-issue/SKILL.md is the cross-repo contract and is read-only from this loop.
This loop is focused exclusively on closed-as-duplicate signals. Other maintainer signals (re-labels, re-opens, follow-up comments) are handled by the separate update-triage loop.
Write surface
This self-improvement loop may only write to:
.agents/skills/dedupe-issue-local/(andSKILL.mdinside it)
It must NOT touch:
.agents/skills/dedupe-issue/SKILL.md(the core contract).agents/skills/triage-issue-local/SKILL.md(owned byupdate-triage)- any other core skill
The self-improvement runner enforces this via a git diff check against allowed prefixes before pushing. A violation aborts the run.
Inputs
- Optional repository override if you are not running from the target checkout.
- Optional time window override when you need something other than the default seven-day lookback.
Workflow
- Verify GitHub CLI auth:
gh auth status
- Aggregate closed-as-duplicate signals for recently closed issues with the bundled script:
python3 .agents/skills/update-dedupe/scripts/aggregate_dedupe_feedback.py
By default this targets the current repo and looks back 7 days. It collects only issues GitHub itself recorded as closed with the duplicate close reason (state_reason == "duplicate") and looks up the canonical issue each was closed against via the issue timeline's marked_as_duplicate event. Ad-hoc maintainer comments that merely mention another issue are intentionally ignored to avoid false positives. The script writes structured JSON to a temporary file and prints the path.
- Read the generated JSON and look for repeated clusters:
- two or more different reporters filed similar issues that maintainers closed as duplicates of the same canonical thread
- an explicit maintainer statement that a class of issue should always be treated as a duplicate of a canonical thread
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 · 69 lines · 49 tokens per session scan A 162fd4008e91
update-dedupe is a skill published in the GitHub repository warpdotdev/oz-for-oss (312 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 817 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 2026-08-30.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.