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/devnpx skills add harshanandak/forge --skill devgit clone --depth 1 https://github.com/harshanandak/forgeWhat 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 | $0.00221 | $0.02913 |
| Opus 5 | $0.00111 | $0.01456 |
| Sonnet 5 | $0.00044 | $0.00583 |
| Haiku 4.5 | $0.00022 | $0.00291 |
Grade A, and why
dev 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 yesterday.
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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement each task from the /plan task list using a subagent-driven loop: implementer → spec compliance reviewer → code quality reviewer per task.
Dev
Chain (HARD-GATE): the ONLY skill you invoke after
devisvalidate. Never open a PR straight fromdev.
This skill reads the task list created by /plan and implements each task using a three-stage subagent loop. TDD is enforced inside each implementer subagent.
Usage
/dev
Setup
Step 1: Load context
# Find task list and design doc
ls docs/work/
Read:
- Task list:
docs/work/YYYY-MM-DD-<slug>/tasks.md— extract ALL task text upfront - Design doc:
docs/work/YYYY-MM-DD-<slug>/plan.md— including ambiguity policy section
Step 2: Create decisions log
Create an empty decisions log at the start of every /dev session:
# docs/work/YYYY-MM-DD-<slug>/decisions.md
Format for each entry:
## Decision N
**Date**: YYYY-MM-DD
**Task**: Task N — <title>
**Gap**: [what the spec didn't cover]
**Score**: [filled checklist total]
**Route**: PROCEED / SPEC-REVIEWER / BLOCKED
**Choice made**: [if PROCEED: what was decided and why]
**Status**: RESOLVED / PENDING-DEVELOPER-INPUT
Step 3: Pre-flight checks
<HARD-GATE: /dev start>
Do NOT write any code until ALL confirmed:
1. git branch --show-current output is NOT main or master
2. git worktree list shows the worktree path for this feature
3. Task list file confirmed to exist (use Read tool — do not assume)
4. Decisions log file created
</HARD-GATE>
Multi-developer conflict check (soft block)
Before starting the per-task loop, check for cross-developer conflicts:
# Auto-sync to get latest team state (non-blocking)
forge sync || true
# Check for conflicts with the current Forge issue
bash scripts/conflict-detect.sh --issue <forge-id>
If exit code 2 (validation error): show error message, abort — do not show conflict prompt.
If exit code 1 (conflicts found):
- Display the conflict output to the developer
- Ask: "Other developers are working in overlapping areas. Proceed anyway? (y/n)"
- If
n: exit cleanly, no side effects - If
y: log override viaforge comment <id> "Conflict override: proceeding despite overlap with <conflicting-issues>", then continue to Per-Task Loop - Audit: record conflict override per OWASP A09
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.
- yesterday First seen · 346 lines · 221 tokens per session scan A d78d4df0d4a3
dev is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 2d ago), licensed MIT. It adds 221 tokens to every session and 2,913 once invoked, about $0.0011 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…