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/harshanandak/forge/gatesnpx skills add harshanandak/forge --skill gatesgit 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/gates)<a href="https://agentmods.dev/skills/harshanandak/forge/gates"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/gates.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 | $0.00235 | $0.01082 |
| Opus 5 | $0.00118 | $0.00541 |
| Sonnet 5 | $0.00047 | $0.00216 |
| Haiku 4.5 | $0.00023 | $0.00108 |
Grade A, and why
gates 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge's gates and rails are default-strong but toggleable. The gates skill is how you flip one off (or back on), record a human-gate approval, and see enforcement state. The stored truth is one field — workflow.gates.<id>.enabled — and the installed hooks read the resolved config at run time, so a disabled rail is genuinely inert, not cosmetically off.
Toggling gates and rails
When to use
- "Disable the gate", "turn off TDD enforcement", "the tdd intent rail is blocking me".
- "Toggle / enable a gate", "loosen enforcement for this repo".
- "Approve a human gate" (record a durable approval event on an issue).
Toggle a gate or rail (the enforcement switch)
forge gate disable <gate-id> # set workflow.gates.<id>.enabled = false in .forge/config.yaml
forge gate enable <gate-id> # set it back to true
An unknown gate id — or disabling a locked gate — errors before anything is written, never mid-run. Because the hooks resolve config at run time, the flip takes effect immediately with no reinstall.
Common rails (default-ON, toggleable)
| Rail | What it enforces | Turn off with |
|---|---|---|
rail.tdd_intent |
Pre-commit TDD gate (source changed ⇒ tests changed). The minimal adoption profile ships it off. |
forge gate disable rail.tdd_intent |
rail.kernel_tracking |
"File every issue" — nothing discussed goes missing. | forge gate disable rail.kernel_tracking |
rail.auto_shepherd |
The autonomous PR-shepherd daemon fire. | forge gate disable rail.auto_shepherd |
The gate.* and rail.* id namespaces are disjoint, so forge gate enable|disable governs both through one flat surface.
Human-gate approval events
forge gate approve <issue-id> <gate-id> # record a durable gate.approved event
forge gate reject <issue-id> <gate-id> # record gate.rejected
forge gate status <issue-id> # list recorded events for that issue (resume-safe)
forge gate check <issue-id> <gate-id> # exit 0 iff gate DISABLED or an approval exists on that issue
What ships with it
2 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.
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 · 81 lines · 235 tokens per session scan A fcd6fa6b4464
gates is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 4d ago), licensed MIT. It adds 235 tokens to every session and 1,082 once invoked, about $0.0012 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…