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/indranilbanerjee/contentforge/cf-environmentnpx skills add indranilbanerjee/contentforge --skill cf-environmentgit clone --depth 1 https://github.com/indranilbanerjee/contentforgeWrote 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/indranilbanerjee/contentforge/cf-environment)<a href="https://agentmods.dev/skills/indranilbanerjee/contentforge/cf-environment"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/contentforge/cf-environment.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 | $0.00156 | $0.01963 |
| Opus 5 | $0.00078 | $0.00981 |
| Sonnet 5 | $0.00031 | $0.00393 |
| Haiku 4.5 | $0.00016 | $0.00196 |
Grade A, and why
cf-environment 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cf-environment — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/contentforge:cf-environment
Detect where ContentForge is running and report which of its capabilities work in that environment. ContentForge has different real-world behavior on each surface because filesystem access, MCP transports, and subprocess invocation all differ.
When to use this skill
- User asks "will my files actually save to my Documents folder?"
- User asks "does this work in Cowork?"
- User reports that
~/Documents/ContentForge/is empty after a run - Before kicking off a long (20-60 min) content pipeline, to set expectations
- During brand-setup, to decide between MCP-Drive and service-account routes
Behavior
Step 1 — Run the environment probe
python scripts/plugin-metadata.py --section environment
This returns JSON with environment (one of cowork-sandbox,
claude-code-windows, claude-code-mac, claude-code-linux,
linux-sandbox-uncertain, unknown — six possible values), filesystem
indicators, a cowork_warning field that's non-null when a sandbox
(confirmed or suspected) is detected, and a signals object (strong /
weak lists) showing exactly which detection heuristics fired — useful
for --verbose or when a user disputes the classification.
Step 2 — Present the capability matrix for the detected environment
Render one of the matrices below based on the JSON environment. The six
values map to three matrices: cowork-sandbox AND linux-sandbox-uncertain
both use the Cowork matrix (uncertain gets a one-line caveat first, see
below); claude-code-windows / -mac / -linux share the local matrix;
unknown gets its own fallback.
cowork-sandbox
Cowork is the recommended environment for teams as of v3.12.9 — it has the friendliest UX, lowest setup friction, and works for non-CLI users. But it requires one extra setup step (connecting Google Drive) because the sandbox filesystem doesn't persist. After Drive is wired, everything works.
Also check: is a Drive MCP available in this session? Scan your available tools for mcp__*drive* or the Anthropic-platform Drive integration. The capability matrix below splits on that.
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.
- 4d ago First seen · 158 lines · 156 tokens per session scan A 32e9fb253e87
cf-environment is a skill published in the GitHub repository indranilbanerjee/contentforge (26 stars, last pushed 18d ago), licensed MIT. It adds 156 tokens to every session and 1,963 once invoked, about $0.0008 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
aeo-audit
Audit how a brand appears across the 6 canonical AI answer surfaces — ChatGPT, Perplexity, Google AI Mode, AI Overviews, Gemini, Copilot — probing 10-25 queries into a numbered output bundle with per-platform visibility scorecards, citation-accuracy checks, a competitor matrix, content gaps, and an optimization…
backlink-gap
Find referring domains that link to your competitors but not to you, ranked by an outreach-priority score (0.40 DR + 0.25 link-overlap + 0.20 traffic + 0.15 topical relevance) — outputs a four-gate quality scorecard, a 30-prospect outreach shortlist, broken-link candidates, and pre-filled outreach templates. Triggers…
ab-test-plan
Design a statistically rigorous A/B or multivariate test plan — If/Then/Because hypothesis, control and variant specs, required sample size per variant (absolute vs relative MDE via sample-size-calculator.py), test duration, guardrail metrics, stopping rules, and go/no-go decision criteria. Triggers on…
aeo-geo
Strategy module for Answer Engine / Generative Engine Optimization — audits AI visibility, restructures content for citation, runs entity-consistency checks across Knowledge Graph, Wikidata, Wikipedia, Crunchbase, and LinkedIn, and produces JSON-LD schema specs, monitoring frameworks, and a 90-day LLM content…
analytics-insights
Marketing measurement module — builds KPI trees per business model, reporting templates (weekly, monthly, QBR, campaign), anomaly root-cause diagnosis, MMM and incrementality guidance, dark-social tracking, and privacy-first cookieless measurement architecture, including the GA4 AI Assistant channel group for…
audience-intelligence
Audience research module — builds six-dimension buyer personas (demographic, psychographic, behavioral, need-state, information, decision), Jobs-to-Be-Done maps, RFM/behavioral/lifecycle segmentation models, anti-personas with exclusion criteria, B2B buying-committee maps, and lookalike seed specs. Triggers on…