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/sidcorp-co/forge/forge-drivenpx skills add SidCorp-co/forge --skill forge-drivegit clone --depth 1 https://github.com/SidCorp-co/forgeWrote 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/sidcorp-co/forge/forge-drive)<a href="https://agentmods.dev/skills/sidcorp-co/forge/forge-drive"><img src="https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-drive.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 | $0.00067 | $0.02497 |
| Opus 5 | $0.00034 | $0.01248 |
| Sonnet 5 | $0.00013 | $0.00499 |
| Haiku 4.5 | $0.00007 | $0.00250 |
Grade A, and why
forge-drive 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-drive
You own one issue from open to done, in one session. Nothing dispatches you again — there is no next job. When you stop, the issue stops.
The cloud is your ledger, not your controller. It records what you declare and blocks exactly two things: deploy and close. Everything else is yours.
The loop
| Phase | You produce | Declared before starting |
|---|---|---|
| 1 · understand | a statement of what is wrong and how you reproduced it | understand |
| 2 · plan | the files you will touch and why, and the branches you rejected | plan |
| 3 · code | a working branch, build green, tests green | code |
| 4 · self-review | your own diff read back against the acceptance criteria | self-review |
| 5 · review | an independent verdict | review |
| 6 · merge | the branch in the base it came from | merge |
| 7 · ship | changelog line, close comment | ship |
Declare each phase with forge_phase before you begin it (action start), and close it when it
finishes (action end, with an outcome). That pair is your resume point: resume_point returns the
newest phase you started and never ended, so a session that dies restarts there instead of at phase
- A phase you never declared did not happen as far as any other session can see — including yours, after a crash.
Phase 5 can send you back to phase 3. That loop has no counter — go around as many times as the
verdict requires. Re-declare code each time so the journal shows the rounds.
What this project told you about itself
These skills ship in the runner binary and are the same on every project. Nothing about this
repo is baked into them. Call forge_config with action get once, before phase 1, and read
projectFacts:
| key | you need it for |
|---|---|
build-commands |
phase 3 — proving the branch compiles |
test-commands |
phase 3 and phase 5 — a verdict with no test run is an opinion |
merge-target |
phase 6, only when the branch does not land in the base it came from |
deploy-policy |
phase 7 — whether shipping deploys, and what gates it |
reproduction |
phase 1 — the URL, the seed data, the account |
done-means |
phase 7 — what this project counts as finished beyond the criteria |
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 · 210 lines · 67 tokens per session scan A ea32fc33cd1b
forge-drive is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,497 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ad-creative
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
adaptive-anti-bot-web-scraping
Adaptive web scraping framework with anti-bot bypass and spider crawling.
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test…
access-gevety-health-biomarker-data
Access your Gevety health data - biomarkers, healthspan scores, biological age, supplements, activities, daily actions, 90-day health protocol, and upcoming tests.
access-exchange-2010-ews-functions
Exchange 2010 EWS integration for emails, calendar, contacts, and tasks.