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 harshanandak/forge --skill forge-cutgit clone --depth 1 https://github.com/harshanandak/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/harshanandak/forge/forge-cut)<a href="https://agentmods.dev/skills/harshanandak/forge/forge-cut"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/forge-cut/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/harshanandak/forge/forge-cut"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/forge-cut.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 | $0.00047 | $0.00690 |
| Opus 5.5 | $0.00019 | $0.00276 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
forge-cut 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 2d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-cut
Intake: file before you forget
Before filing, route an unclear goal or done condition to forge-intake. Route open decisions to forge-intake; read framing.md for facts and decision records before slicing.
forge issue create --input '{"title":"...","kind":"task","labels":["p2"],"parent":"<intent id>","dependsOn":["<dep id>"],"body":"..."}'
Kind: task, bug, feature or epic. Priority is one label of p0, p1, p2, p3, p4. File settled work and move on; fixes outside the current slice stay filed.
Use intake's intent issue as parent when it created one, otherwise the epic. Set dependsOn at creation; omit it for unblocked slices.
Slice body: all six sections
- Behaviour: the demoable, end-to-end user change, sized for one fresh context.
- Failing check: the named check that fails before and passes after.
- Done boundary: what is in. File anything beyond it.
- Touches / Needs / Owns: files read, required from main, and written.
- Door: reversible, or one-way (publish, force-push, prod-write, migration-apply, delete-branch, delete-worktree, merge-to-autodeploy, global-config).
- Size: Aim at 400 changed lines; split above 800. If deletions exceed twice the additions, do not split and score light. Otherwise sum risk: churn over 518 lines +2, over 10 files +2, touches
coreorblocks+1. Bands: light 0-1, standard 2-3, heavy 4-5. Record estimates, points and band.
Order
- Write a graph of demoable, one-context slices as issues in Forge. Put prefactors and contract slices first; a need missing from main gets a contract slice.
- For later edits, use
forge issue dep --input '{"id":"<slice>","target":"<dep>","action":"add","expectRevision":<n>}'; hold the claim and read the revision fromforge issue showfirst, then release withforge issue release <slice>. - Each slice ships green alone. Wide refactors run expand, migrate in batches, then contract; each step is a slice and contract depends on every migration batch.
- Uncertain work goes last. For rename or removal, search the whole repo first and list every hit under Touches.
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.
- 2d ago First seen · 39 lines · 47 tokens per session scan A 16714d71fad0
forge-cut is a skill published in the GitHub repository harshanandak/forge (0 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 690 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.