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/bostonorange/claude-code-framework/developnpx skills add BostonOrange/claude-code-framework --skill developgit clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWhat 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 | $0.00037 | $0.02476 |
| Opus 5 | $0.00018 | $0.01238 |
| Sonnet 5 | $0.00007 | $0.00495 |
| Haiku 4.5 | $0.00004 | $0.00248 |
Grade A, and why
develop 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop
End-to-end development cycle: fetch ticket, analyze, implement, validate, fix, commit, PR.
Usage
/develop TICKET-1234
/develop 1234
/develop TICKET-1234 --factory # Factory mode (all auto-defaults)
If no ticket ID provided, ask for it. If user pastes story content directly, skip Phase 1 and ask for a ticket ID for naming.
Factory Mode
When invoked with --factory (or from /factory), all interactive gates use auto-defaults:
| Decision Point | Interactive (default) | Factory Mode |
|---|---|---|
| Phase 2: Gap analysis | Ask user if major gaps | Skip (readiness gate already passed) |
| Phase 3: Worktree vs main repo | Ask user | Always worktree |
| Phase 5: Validation | Deploy + code standards | Code standards only (CI handles deployment) |
| Phase 7: PR label | No label | Add factory label (triggers CI deploy) |
| Phase 7: Ticket state transition | Ask user | Auto-transition to review state |
| Phase 8: Push to tracker | Ask user | Auto-push |
| Phase 6: On standards failure | Present options to user | Halt + notify |
CRITICAL — when invoked from
/factory:/develop --factoryhandles Phases 1-5 (fetch, analyze, branch, implement, code standards). It does NOT push, create a PR, or update the tracker. Control returns to/factorywhich may run additional validation BEFORE pushing.
Phase 1: Fetch Ticket from Tracker
Parse ticket ID from input. Accept TICKET-1234 or just 1234.
{{TRACKER_FETCH_TICKET}}
Extract from response:
- Title
- State/Status
- Type (story, bug, task)
- Assignee
- Description
- Acceptance Criteria
Display summary table, then show cleaned Description and Acceptance Criteria.
Auto-transition to In Progress
After displaying the summary, check state. If not "In Progress" (or equivalent):
{{TRACKER_SET_IN_PROGRESS}}
Confirm to user: "Set TICKET-{id} to In Progress (assigned to {display_name})"
Phase 2: Analyze & Refine
Factory mode: Skip this phase — /check-readiness already validated the ticket.
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 · 329 lines · 37 tokens per session scan A c904db55efe2
develop is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,476 once invoked, about $0.0002 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…