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 kubev2v/forklift-console-plugin --skill i18n-memsourcegit clone --depth 1 https://github.com/kubev2v/forklift-console-pluginWrote 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/kubev2v/forklift-console-plugin/i18n-memsource)<a href="https://agentmods.dev/skills/kubev2v/forklift-console-plugin/i18n-memsource"><img src="https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/i18n-memsource/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/kubev2v/forklift-console-plugin/i18n-memsource"><img src="https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/i18n-memsource.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 | $0.00067 | $0.03356 |
| Opus 5.5 | $0.00027 | $0.01342 |
| Sonnet 5.5 | $0.00013 | $0.00671 |
| Haiku 4.5 | $0.00007 | $0.00336 |
Grade C, and why
i18n-memsource scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf po-files How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i18n Memsource Workflow
Manages the full translation lifecycle: uploading strings to Memsource/Phrase, downloading translated files, creating PRs, and tracking status.
State
Read .agents/skills/i18n-memsource/state.json for current sprint, version, and project ID. Update it after each upload.
Prerequisites
Personal setup (per developer)
Machine-specific CLI paths and auth helpers are not in this shared skill. They live in a gitignored personal overlay:
- If
.agents/skills/personal-i18n-memsource/SETUP.mdexists, read it first for this developer's CLI path and auth flow. - If missing, use the generic discovery below and ask the user to authenticate.
One-time setup for each developer:
mkdir -p .agents/skills/personal-i18n-memsource
cp .agents/skills/i18n-memsource/personal-setup.example.md \
.agents/skills/personal-i18n-memsource/SETUP.md
# edit SETUP.md for your machine
Memsource CLI
The memsource CLI is a Python package (memsource-cli) installed via pip3. It
may not be on the default PATH. Locate and export it:
MEMSOURCE_BIN=$(python3 -c "import shutil; print(shutil.which('memsource') or '')")
if [ -z "$MEMSOURCE_BIN" ]; then
MEMSOURCE_BIN=$(find "$HOME/Library/Python" -name memsource -type f 2>/dev/null | head -1)
fi
export PATH="$(dirname "$MEMSOURCE_BIN"):$PATH"
Authentication (credentials stay with the user)
Do not read ~/.memsourcerc contents, Memsource passwords, or tokens into
the agent context. Phrase is a paid external service — treat credentials like
any other secret.
Preferred flow:
- Prefer the personal
SETUP.mdauth steps when that file exists. - Otherwise ask the user to authenticate in their own terminal and confirm
memsource auth whoamiworks (and thatMEMSOURCE_TOKENis exported in the shell they will use fornpm run memsource-*). - The agent may run extract/export/validation without credentials
(
npm run i18n,npm run export-pos, PO checks). - For upload/download/status, either:
- follow personal SETUP.md (e.g.
source ~/.memsourcerc+ login — never read credential file contents into agent context), or - the user runs the
memsource-*/memsource job listcommands themselves, or - the user has already exported a short-lived
MEMSOURCE_TOKENin the shared shell (never paste the password into chat).
- follow personal SETUP.md (e.g.
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.
- 26d ago Changed · +2 lines 72a8a7ab3dbe
- 1mo ago Changed · +52 lines d8947edec45c
- 2mo ago First seen · 331 lines · 67 tokens per session scan C fe49456fee63
i18n-memsource is a skill published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 3,356 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
i18n-memsource compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| i18n-memsourcekubev2v/forklift-console-plugin | Skill | 11 | today | Apache-2.0 | C | 67 | Claude Code, Codex |
| chinese-documentationjnMetaCode/superpowers-zh | Skill | 8.5k | today | MIT | A | 62 | Claude Code |
| intl-expansionalirezarezvani/claude-skills | Skill | 30k | 3d ago | MIT | A | 27 | Claude Code |
| azure-ai-translation-text-pymicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 60 | Claude Code |
| hardenfengshao1227/ccg-workflow | Skill | 6.0k | 14d ago | MIT | A | 62 | Claude Code |
| edit-sitemicrosoft/power-platform-skills | Skill | 1.2k | today | MIT | A | 104 | Claude Code |
| tiktok-shop-cross-bordernexscope-ai/eCommerce-Skills | Skill | 1.4k | 5d ago | MIT | A | 55 | Claude Code, Codex |