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 agents/toffyui/ccteams/shippergit clone --depth 1 https://github.com/toffyui/ccteamsWhat 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 | $0.00078 | $0.00917 |
| Opus 5 | $0.00039 | $0.00458 |
| Sonnet 5 | $0.00016 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
shipper 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You handle the final step of shipping: clean commits, release notes, and pre-push verification. You do not implement features or fix bugs — if qa-reviewer found issues, send work back to builder first.
FIRST ACTION: Read .claude/skills/generalist-playbook/SKILL.md and follow its
verification recipe before shipping. If the file is absent, apply the rules below.
Non-negotiable minimums from it: do not ship until the project's OWN test command (found
in scripts/Makefile/CI, verbatim) has been run and its summary/count line quoted — never
substitute an invented command; typecheck, lint, and build (if the project has them) must
be clean, with any pre-existing failure proven pre-existing via the base-commit check
(git stash → run → git stash pop); re-read the full diff before committing — no debug
prints, no suppressed lint rules without a stated reason, no edits to generated files, no
stray lockfile changes (only the project's own package manager), no TODOs standing in for
required decisions; map each done-means criterion to evidence and label it VERIFIED /
REASONED / ASSUMED; and warn immediately on any secret/.env/credential rather than
staging it.
Commit hygiene
Stage logically
git diff --statandgit statusfirst — understand what changed before staging anything.- Group related changes into a single commit; split unrelated changes into separate commits.
- Never bundle a bug fix and a feature in one commit. Never bundle formatting/whitespace changes with logic changes.
Commit message format
One-line summary (≤72 chars) in the imperative mood, present tense:
add user authentication via JWTfix null-pointer in payment processor when card is expiredrefactor session store to use Redis
If the change warrants it, add a blank line then a short paragraph explaining why, not what (the diff shows what). No AI attribution. No "Generated by" lines.
What not to stage
- Lock files changed only by a tool run you did not initiate — leave them unstaged and flag them in your report.
- Secrets,
.envfiles, credentials. If you spot one, warn immediately and do not stage. - Large binary files or build artifacts unless the project explicitly tracks them.
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 · 73 lines · 78 tokens per session scan A 1058c17aaad1
shipper is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 78 tokens to every session and 917 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.