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 pierreprudh/KLIDE --skill klide-skillgit clone --depth 1 https://github.com/pierreprudh/KLIDEWrote 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/pierreprudh/klide/klide-skill)<a href="https://agentmods.dev/skills/pierreprudh/klide/klide-skill"><img src="https://agentmods.dev/badge/skills/pierreprudh/klide/klide-skill/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/pierreprudh/klide/klide-skill"><img src="https://agentmods.dev/badge/skills/pierreprudh/klide/klide-skill.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 | $0.00053 | $0.00363 |
| Opus 5.5 | $0.00021 | $0.00145 |
| Sonnet 5.5 | $0.00011 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
klide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Continue in Klide
Klide resumes this exact Claude Code session in one of its AI panels
(claude --resume <id>), in the project this session runs in. Nothing is
copied or summarized: it is the same session, so claude --resume in a
terminal still finds it afterwards.
-
Run exactly this command, nothing else:
open "klide://resume?provider=claude-code&session=$CLAUDE_CODE_SESSION_ID"CLAUDE_CODE_SESSION_IDis set in this shell by Claude Code. Klide reads the project from the session's own transcript; add&project=<url-encoded absolute path>only if Klide says it could not. -
If
openreports that no application handles the URL, Klide is not installed in /Applications (links reach the installed app, never atauri devbuild). Say so and stop. -
Then tell the user in one line: Klide is opening this session, and they should end this terminal session (
/exit) before typing there, because two processes on one session would both write its transcript.
Do not put the conversation into the link, do not write a summary file, and do not run anything else.
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.
- 3d ago First seen · 35 lines · 53 tokens per session scan A b3f1ebc9000c
klide is a skill published in the GitHub repository pierreprudh/KLIDE (6 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 363 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 2026-10-11.
Other skills, from other repositories
local-project-context
The local task workspace, the build/test commands the hand-off gate runs, and the file and exploration tools. Use when starting work in a task workspace or before running any build, test or verification command.
concise-mode
Use this skill to enforce high-density, zero-filler, token-efficient communication. Strips conversational fluff, polite preamble, redundant summaries, and repetitive apologies to maximize reasoning density, reduce latency, and conserve context window budget.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…