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 Espenandreass1/agentslice --skill explore-locallygit clone --depth 1 https://github.com/Espenandreass1/agentsliceWrote 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/espenandreass1/agentslice/explore-locally)<a href="https://agentmods.dev/skills/espenandreass1/agentslice/explore-locally"><img src="https://agentmods.dev/badge/skills/espenandreass1/agentslice/explore-locally/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/espenandreass1/agentslice/explore-locally"><img src="https://agentmods.dev/badge/skills/espenandreass1/agentslice/explore-locally.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 | $0.00026 | $0.00271 |
| Opus 5.5 | $0.00010 | $0.00108 |
| Sonnet 5.5 | $0.00005 | $0.00054 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
explore-locally 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.
What it actually says
Explore Locally
Read
Verify agentslice.policy.json against the Git root. Read the minimal preflight and only source files relevant to the experiment.
Guardrails
- Ask which concrete current user problem is being tested.
- Work only on
explore/<idea>(or the policy's configured prefix). - Create no PR, preview, spec, QA report, release note, checkpoint, workflow-state update, merge, or deployment.
- Keep the experiment short and reversible. It is not release evidence.
- Stop and promote promptly if a sensitive policy area is touched: auth/ownership, data/RLS, public contracts/pages, providers, commerce, hosting, CI, or production data.
Steps
- State the hypothesis and smallest observable check.
- Make only the local changes needed to test it.
- Run the smallest relevant local check.
- Either abandon the branch or promote useful evidence to a PR with a user problem, lane, scope, test plan, and rollback.
Output
Report hypothesis, result, files changed, one-line check result, and abandon or promote decision. Do not create process paperwork.
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 · 30 lines · 26 tokens per session scan A cf22e9c45372
explore-locally is a skill published in the GitHub repository Espenandreass1/agentslice (4 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 271 once invoked, about $0.0001 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 2026-09-06.
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.