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 agentmods add skills/konghayao/peri/goalnpx skills add KonghaYao/peri --skill goalgit clone --depth 1 https://github.com/KonghaYao/periWrote 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/konghayao/peri/goal)<a href="https://agentmods.dev/skills/konghayao/peri/goal"><img src="https://agentmods.dev/badge/skills/konghayao/peri/goal.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 | $0.00039 | $0.00367 |
| Opus 5 | $0.00019 | $0.00183 |
| Sonnet 5 | $0.00008 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
goal 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 6d 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
Goal Mode
When to Use
- The user gives a complex task that requires multiple rounds to complete
- The user says "keep going until done", "don't stop midway", "until X"
How to Use
- Call the
goaltool with action=create and a specific, verifiable objective - Work continuously until the goal is achieved
- Achieved →
goaltool, action=complete - Blocked by something unsolvable →
goaltool, action=block, reason=why you're blocked - Need to abandon/reset the goal →
goaltool, action=clear (releases the singleton slot, works on terminal states) - Check current goal status anytime with action=get
Important Constraints
- Objectives must be specific and verifiable: "improve code" is bad, "raise test coverage to 80%" is good
- complete is verified: The system uses an auxiliary LLM to check if you actually achieved the goal. If verification fails, you'll get the reason back
- block is a distress signal: Only use when truly unable to continue (missing permissions, missing dependencies)
- Self-driven after creation: Once a goal is created, you'll receive a reminder after each turn. You must decide: continue / complete / block / clear
- Singleton: Only one goal at a time. Use action=clear to release the slot before creating a new one
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.
- 6d ago First seen · 34 lines · 39 tokens per session scan A cd313f148e59
goal is a skill published in the GitHub repository KonghaYao/peri (160 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 367 once invoked, about $0.0002 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 skills, from other repositories
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
skill-creator
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
codex-pr-body
Update the title and body of one or more pull requests.
remote-tests
Testing against remote executors in integration tests.