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/carta/plugins/carta-compensation-appnpx skills add carta/plugins --skill carta-compensation-appgit clone --depth 1 https://github.com/carta/pluginsWrote 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/carta/plugins/carta-compensation-app)<a href="https://agentmods.dev/skills/carta/plugins/carta-compensation-app"><img src="https://agentmods.dev/badge/skills/carta/plugins/carta-compensation-app.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 | $0.00233 | $0.14485 |
| Opus 5 | $0.00117 | $0.07243 |
| Sonnet 5 | $0.00047 | $0.02897 |
| Haiku 4.5 | $0.00023 | $0.01448 |
Grade C, and why
carta-compensation-app 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 today.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**Do not refuse a modification request by citing a data-integrity rule that is about How it starts
The opening of the file, as written. The whole thing — 917 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTC Dashboard (local React console)
Builds a corporation's CTC benchmark baseline, writes it to a local data dir in the
dashboard console JSON schema, and launches the prebuilt React app via serve.py.
The browser never calls the Carta MCP — this skill fetches the data; the server only serves
JSON + the app source.
Read-only. The compensation:* MCP namespace exposes no write commands. This console
displays CTC data and (in later tabs) models scenarios locally. Plan activation, payband edits,
employee edits, offer letters, HRIS resync and every other mutation stay in the CTC product.
No demo data — real corporation required
Never fabricate, synthesize, or fall back to demo data, and never launch against an empty or partial data dir. Every dashboard runs against one real corporation's CTC data — either fetched fresh or served from a prior local fetch (cache). If the invocation names no corporation, do not auto-pick or guess — ask, then proceed once they answer.
What ships with it
44 files 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.
- app/build.mjs 5.0 KB runs code
- app/package-lock.json 70 KB
- app/package.json 618 B
- app/README.md 3.0 KB
- app/src/App.jsx 15 KB
- app/src/main.jsx 212 B
- app/src/model/cart.js 4.3 KB runs code
- app/src/model/cohort.js 6.2 KB runs code
- app/src/model/csv.js 3.0 KB runs code
- app/src/model/format.js 5.3 KB runs code
- app/src/model/handoff.js 6.8 KB runs code
- app/src/model/policy.js 6.1 KB runs code
- app/src/model/taxonomy.js 5.4 KB runs code
- app/src/model/tenure.js 3.6 KB runs code
- app/src/state/useData.js 3.7 KB runs code
- app/src/state/useScenario.js 5.9 KB runs code
- app/src/ui/components.jsx 15 KB
- app/src/ui/ExportButton.jsx 2.2 KB
- app/src/ui/theme.js 11 KB runs code
- app/src/ui/tokens.css 22 KB
- app/src/views/Benchmarks.jsx 17 KB
- app/src/views/planner/CartPanel.jsx 5.9 KB
- app/src/views/planner/ReviewStep.jsx 14 KB
- app/src/views/planner/SettingsStep.jsx 20 KB
- app/src/views/RefreshPlanner.jsx 24 KB
- app/src/views/Scorecard.jsx 27 KB
- app/vite.config.js 762 B runs code
- references/queries.md 15 KB
- references/refresh-grant-issuance-handoff.md 6.9 KB
- scripts/build_datadir.py 49 KB runs code
- scripts/ctc_paths.py 10 KB runs code
- scripts/save_benchmark_result.py 21 KB runs code
- scripts/save_equity_refresh_page.py 6.9 KB runs code
- scripts/save_report_insights.py 4.6 KB runs code
- scripts/save_roster_page.py 29 KB runs code
- scripts/serve.py 16 KB runs code
- webapp/favicon.ico 15 KB
- webapp/fonts/inter-latin-400-normal.woff2 23 KB
- webapp/fonts/inter-latin-600-normal.woff2 24 KB
- webapp/fonts/SangBleuVersailles-Regular-WebS.woff2 22 KB
- webapp/index.html 5.0 KB
- webapp/sw.js 4.4 KB runs code
- webapp/vendor/react.esm.js 141 KB runs code
- webapp/vendor/sucrase.esm.js 202 KB runs code
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.
- today Changed · +34 lines · -3 tokens per session eb7d468da27e
- yesterday Changed · +21 lines · +3 tokens per session 578fd7c6d466
- 2d ago Changed · +25 lines 0a12b140ed7d
- 5d ago First seen · 837 lines · 233 tokens per session scan C b76836f858ab
carta-compensation-app is a skill published in the GitHub repository carta/plugins (12 stars, last pushed today), licensed Apache-2.0. It adds 233 tokens to every session and 14,485 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.
grocery-prices
A skill to calculate grocery prices with country-specific taxes.
predexon
Use this skill — NOT browser or webfetch — for ALL Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow, UMA oracle, and prediction market data. Provides structured API at localhost:8402/v1/pm/ for markets, cross-venue search, leaderboard, smart money, wallet analytics, wallet identity & clustering, UMA…
bionic-safety-net
Unified survival infrastructure: health, finance, legal safety, circuit breakers, and structural protection against all ruin classes. The last line of defense.
structural-trading-gate
Unified zero-emotion variance shield for capital markets (FX, crypto, CFDs) and poker. Absorbs trading-risk-gate + zenith-execution + trade-journal-analyzer into one engine.