Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add gwittebolle/claude-carbon/plugin install claude-carbonWrote 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/gwittebolle/claude-carbon/carbon-card)<a href="https://agentmods.dev/skills/gwittebolle/claude-carbon/carbon-card"><img src="https://agentmods.dev/badge/skills/gwittebolle/claude-carbon/carbon-card/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/gwittebolle/claude-carbon/carbon-card"><img src="https://agentmods.dev/badge/skills/gwittebolle/claude-carbon/carbon-card.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 | $0.00015 | $0.01082 |
| Opus 5 | $0.00008 | $0.00541 |
| Sonnet 5 | $0.00003 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
carbon-card scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the following bash script and present the output to the user. Show the exported file paths so they can share the PNGs, and tell them the folder has been opened in their file manager.
#!/usr/bin/env bash
# Locate the install wired into the status line (honours CLAUDE_CONFIG_DIR),
# then fall back to CLAUDE_PLUGIN_ROOT / CLAUDE_CARBON_DIR / the default path.
# Windows (Git Bash): CLAUDE_* variables and the paths stored in settings.json can
# arrive in the native "C:\Users\..." spelling, which bash cannot open. cygpath
# ships with Git for Windows; everywhere else this is the identity function.
ccp() {
case "${OSTYPE:-}" in msys*|cygwin*) ;; *) printf '%s' "$1"; return 0 ;; esac
case "$1" in
[A-Za-z]:[\\/]*|*\\*) cygpath -u "$1" 2>/dev/null || printf '%s' "$1" ;;
*) printf '%s' "$1" ;;
esac
}
CFG="$(ccp "${CLAUDE_CONFIG_DIR:-$HOME/.claude}")"
REPO_DIR=""
if command -v jq >/dev/null 2>&1 && [ -f "$CFG/settings.json" ]; then
SL_CMD="$(jq -r '.statusLine.command // empty' "$CFG/settings.json" 2>/dev/null)"
# statusLine.command stores a shell-escaped path: expand ~ and unescape spaces
SL_CMD="${SL_CMD//\\ / }"; SL_CMD="${SL_CMD/#\~/$HOME}"; SL_CMD="$(ccp "$SL_CMD")"
[ -n "$SL_CMD" ] && [ -f "$SL_CMD" ] && REPO_DIR="$(cd "$(dirname "$SL_CMD")/.." 2>/dev/null && pwd)"
fi
[ -z "$REPO_DIR" ] && [ -n "${CLAUDE_PLUGIN_ROOT:-}" ] && REPO_DIR="$(ccp "$CLAUDE_PLUGIN_ROOT")"
[ -z "$REPO_DIR" ] && [ -n "${CLAUDE_CARBON_DIR:-}" ] && REPO_DIR="$(ccp "$CLAUDE_CARBON_DIR")"
if [ -z "$REPO_DIR" ]; then
# Pure marketplace installs reach here: no statusLine.command in settings.json and
# no CLAUDE_PLUGIN_ROOT in a skill's bash env. Pick the newest cached plugin copy,
# the same scan as statusline.sh CACHE_LATEST.
CACHE_LATEST=""
for D in "$CFG/plugins/cache"/*/claude-carbon/*/; do
[ -f "${D}scripts/generate-report.sh" ] || continue
if [ -z "$CACHE_LATEST" ] || [ "$(printf '%s\n%s\n' "$CACHE_LATEST" "$D" | sort -V | tail -1)" = "$D" ]; then
CACHE_LATEST="$D"
fi
done
[ -n "$CACHE_LATEST" ] && REPO_DIR="${CACHE_LATEST%/}"
fi
[ -z "$REPO_DIR" ] && REPO_DIR="$HOME/code/claude-carbon"
bash "$REPO_DIR/scripts/generate-report.sh"
The script prints the export directory on its final line (Done. <dir>/) and a Totals since ... line just above it. The directory is the user's Downloads folder (~/Downloads/claude-carbon/, or CLAUDE_CARBON_EXPORT_DIR when set), and the script has already opened it in the file manager: Finder with the summary card selected on macOS, Explorer on Windows, the default file manager on Linux (skipped when CLAUDE_CARBON_NO_OPEN is set or no display is available). Show the export path exactly as printed, it is already in the platform's native spelling, and say the folder should now be open in front of them.
Then offer a ready-to-paste social post draft (LinkedIn or X) built ONLY from the numbers on the Totals since ... line: CO2e total, cost, the car-km equivalence, session count. The car figure on that line follows the detected locale (ADEME km on a French or undetected locale, EPA miles on a US one, world-average km otherwise) and matches the EN card; the FR card always shows the ADEME figure. The line names its factor in the parenthesis after "by car". Quote the line as printed, unit and factor included, rather than recomputing it. Write it in the user's working language. Keep the register strictly factual: numbers and equivalences, no self-congratulation, no green-virtue framing, no hashtag pile (two at most). Do not add a credit line for the tool in the draft; the card's footer already carries the repo and tokenclimate.com attribution. If the user asks for changes, iterate on the draft, never on the numbers.
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.
- 8d ago Changed c5b98ce3087e
- 9d ago Changed · +10 lines 282ad4c30c58
- 13d ago First seen · 43 lines · 15 tokens per session scan A 457b2c43de57
carbon-card is a skill published in the GitHub repository gwittebolle/claude-carbon (193 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,082 once invoked, about $0.0001 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
ccdb
A search tool for carbon emission factors, which are values used to estimate emissions from activities or materials. It queries the Carbonstop CCDB database and returns structured results.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
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.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.