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/promotenpx skills add BostonOrange/claude-code-framework --skill promotegit 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 | $0.00020 | $0.01201 |
| Opus 5 | $0.00010 | $0.00600 |
| Sonnet 5 | $0.00004 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
promote 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote
Produce an evidence package for moving an internal Next.js business app from Layer 1 to Layer 2. This is not an approval step and must not update LAYER.md to 2; IT does that after sign-off.
Usage
/promote
/promote --layer 2
Only Layer 2 is supported. Layer 3 is a formal project, not a checklist promotion.
Preconditions
The target repo should be an internal Next.js business app created from this framework:
LAYER.mdexists and has no<<intake:*>>tokens.package.json,prisma/schema.prisma,src/lib/auth,src/lib/blob/client.ts, andsrc/lib/audit-log/repository.tsexist.docs/deployment-layers.mdexists in the provisioned repo, or the source template doc is available from the framework.
If LAYER.md.template exists or intake tokens remain, stop. The repo has not been provisioned correctly.
Process
Phase 1: Mechanical Checks
Run read-only checks first and record the command/result in the report.
Required checks:
- Confirm the working tree is clean:
git status --short - Confirm
LAYER.mdexists andLAYER.md.templatedoes not:test -f LAYER.md && test ! -f LAYER.md.template - Confirm no intake tokens remain in stamped seed files:
The command should produce no output. Documentation files may still mention token names as examples.grep -n "<<intake:" LAYER.md README.md CLAUDE.md 2>/dev/null - Confirm no committed local env files:
git ls-files | grep -E '(^|/)\.env($|\.|/)' | grep -vE '(^|/)\.env\.example$'.env.exampleis allowed. Any committed.env,.env.local,.env.production, or equivalent is a blocker. - Run a focused secret scan over tracked files:
Treat findings in examples/docs as warnings unless they contain real-looking values.git grep -n -E 'sk-proj-|sk-org-|AKIA[0-9A-Z]{16}|-----BEGIN .*KEY-----|client_secret|password' -- . - Confirm Layer 2-relevant app boundaries exist:
test -f src/lib/auth/oidc.ts test -f src/lib/blob/client.ts test -f src/lib/audit-log/repository.ts test -f prisma/schema.prisma - Run the project validation commands when dependencies are installed:
If dependencies are missing, record that validation could not run and list the missing prerequisite.npm run typecheck npm run lint npm run build npm audit --audit-level=high
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 · 159 lines · 20 tokens per session scan A a5fecccf4d58
promote is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,201 once invoked, about $0.0001 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…