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/vimalk0703/shipworthy/context-managernpx skills add Vimalk0703/shipworthy --skill context-managergit clone --depth 1 https://github.com/Vimalk0703/shipworthyWrote 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/vimalk0703/shipworthy/context-manager)<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/context-manager"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/context-manager.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 | $0.00054 | $0.01743 |
| Opus 5 | $0.00027 | $0.00872 |
| Sonnet 5 | $0.00011 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00174 |
Grade A, and why
context-manager 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager
Purpose
Context quality matters more than model capability. This skill teaches Claude HOW to build maximum project understanding by routing knowledge to the right place and following the 7 principles that make context survive across sessions, context compaction, and multiple Claude instances.
The 7 Principles of Context Engineering
1. Prohibitions Beat Descriptions
Rules framed as what NOT to do survive context decay. Descriptive rules drift.
| Wrong | Right |
|---|---|
| We use Supabase for our database. | NEVER use Prisma. NEVER use Drizzle. Supabase only. |
| We prefer pino for logging. | NEVER use console.log — pino is already configured. |
| We use Jest for testing. | NEVER use Mocha or Vitest. Jest only. |
2. Anchor Rules to File Paths
Verifiable rules reference the actual file tree. Abstract rules drift because Claude has nothing concrete to check against.
| Wrong | Right |
|---|---|
| Use Zod for validation. | All validation schemas live in src/schemas/. NEVER inline validation. |
| We use Express with a standard structure. | All routes in src/routes/. All middleware in src/middleware/. All models in src/models/. |
| Tests should be nearby. | Tests colocated: src/foo.ts has src/foo.test.ts. NEVER put tests in a separate tests/ tree. |
3. Negative Examples Anchor Harder
A regression fence of documented past mistakes works better than abstract best practices. Claude avoids repeating documented failures more reliably than it follows aspirational rules.
The regression fence lives at .shipworthy/regression-fence.md and is loaded every session as hard constraints. See the Regression Fence section below.
4. Constitution vs Working Memory
Two files, two jobs:
- CLAUDE.md = Constitution. Stable. Rarely changing. Stack locks, prohibitions, directory structure, non-negotiable rules. Read every session.
.shipworthy/sessions/= Working memory. Dynamic. Updated every session. What happened, what's in progress, what's next.
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 · 147 lines · 54 tokens per session scan A 87da1b66bba0
context-manager is a skill published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,743 once invoked, about $0.0003 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
hedgehog-planning-intake
Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…
inbound-triage
Maintainer-only. Use when triaging inbound GitHub issues and pull requests on skyf0xx/hedgehog — "triage the issues", "check the PRs", "review inbound", "what's in the queue". Reads each item read-only, judges it for security and for whether it is real, then fixes and closes or comments and closes. Not part of the…
bmad-product-brief
Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.
bmad-revendor
Maintainer-only. Use when re-vendoring vendor-skills/BMAD/ against a newer BMAD-METHOD commit — "update BMAD", "re-vendor BMAD", "bump the BMAD pin". Not part of the Hedgehog discipline a consuming project copies; this only applies to the Hedgehog repo itself.
bmad-deep-recon
Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…
conventional-commits
Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…