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 LucasSantana-Dev/sharekit --skill loopgit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/loop)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/loop"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/loop/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/lucassantana-dev/sharekit/loop"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/loop.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 | $0.00099 | $0.00509 |
| Opus 5.5 | $0.00040 | $0.00204 |
| Sonnet 5.5 | $0.00020 | $0.00102 |
| Haiku 4.5 | $0.00010 | $0.00051 |
Grade A, and why
loop 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
loop
Cycle
-
Inspect the smallest missing evidence. Done when: smallest gap identified, next action clear
-
Act on the smallest coherent change. Done when: artifact created and narrow surface-area check passed
-
Verify with narrow checks first. Done when: narrow checks pass (lint/unit test/spot-check only)
-
Checkpoint the result.
-
Repeat until done or blocked.
Stop conditions
Stop and re-route if:
- the evidence no longer supports the current path
- the diff grows beyond the intended scope
- the same failure repeats without progress
- the work becomes multi-step enough to require
plan - context budget exceeds 75% → emit
handoff, then stop the loop - cumulative tool-result bytes >50KB without progress → summarize + drop noise before next iteration
Stuck protocol
If the same task has been attempted >2 times without measurable progress (same failure repeating, diff not advancing), stop the loop and emit: "Stuck: [task], attempt N, last blocker: [X]." Switch to a different approach or tool. After 2 approach switches fail without progress, escalate to the user — do not keep cycling silently.
Output (per checkpoint)
One line per completed step: verdict + artifact produced. Report only what changed or failed. Do not narrate steps that passed cleanly.
Parallel mode
If a Monitor task is running (CI settle, build, long test), do NOT busy-wait. Pick up an independent priority — refactor a different file, draft a memory note, answer an open review thread — and resume the original loop when the monitor fires its event.
Rule: at most one Monitor active per loop; otherwise events collide.
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 · 53 lines · 99 tokens per session scan A cfc49388d29d
loop is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 509 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.