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 skills add xobotyi/cc-foundry --skill handoffgit clone --depth 1 https://github.com/xobotyi/cc-foundryWrote 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/xobotyi/cc-foundry/handoff)<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/handoff"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/handoff/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/handoff"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00035 | $0.01657 |
| Opus 5.5 | $0.00014 | $0.00663 |
| Sonnet 5.5 | $0.00007 | $0.00331 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
handoff 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 1mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A handoff document is a prompt. The receiver has no access to this conversation, so everything it needs must be on the page — and everything it does not need competes with what it does.
Mode
$mode selects the receiver. Empty means self.
- self — the receiver holds your project knowledge. Task state, decisions, remaining work. No codebase orientation.
- teammate — the receiver may hold none of it. Adds codebase orientation, skill and tool pointers, and conventions.
Triage
Two passes, in this order. A single pass sorts for precision and loses the subtle context that turns out to be load-bearing — which is the documented failure of aggressive compaction.
- Recall. Collect everything relevant. Over-collect; nothing is cut yet.
- Precision. Cut what the categories below mark as noise, and only then.
Keep — state that does not survive the boundary any other way:
- Decisions and their rationale, including options considered and rejected. A rejected option that arrives without its reason gets proposed again by the receiver
- Constraints discovered during the work
- Contingencies — the failure modes you can foresee and the receiver cannot. "If the integration test still fails after a rebuild, it is the fixture cache, not the code." This is the element handoffs omit most often
- External resource identifiers — URLs, issue IDs, file paths with line numbers, branch names, commit SHAs
- Verification state, in both directions: what was checked and its result, and what was not checked
- Negative state — work that looks started and is not. "No branch, no edit, no commit" stops the receiver assuming a base that does not exist
- Remaining work in priority order
- Blockers and open questions
Drop — noise in transfer:
- Intermediate exploration and search paths
- Content already committed to files or git history
- Content already captured in an upstream artifact — a PRD, plan, ADR, or tracker issue. Reference it by path or ID
- Anything derivable from the codebase — file structure, function signatures
- Raw tool output
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.
- 1mo ago First seen · 177 lines · 35 tokens per session scan A 6e8d1bb061eb
handoff is a skill published in the GitHub repository xobotyi/cc-foundry (22 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 1,657 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
remove
Remove a deployed framework or addon from the current workspace.