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 furkantokkan/agent-foundry --skill daily-handoffgit clone --depth 1 https://github.com/furkantokkan/agent-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/furkantokkan/agent-foundry/daily-handoff)<a href="https://agentmods.dev/skills/furkantokkan/agent-foundry/daily-handoff"><img src="https://agentmods.dev/badge/skills/furkantokkan/agent-foundry/daily-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/furkantokkan/agent-foundry/daily-handoff"><img src="https://agentmods.dev/badge/skills/furkantokkan/agent-foundry/daily-handoff.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00086 | $0.01390 |
| Opus 5.5 | $0.00034 | $0.00556 |
| Sonnet 5.5 | $0.00017 | $0.00278 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
daily-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 24d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Handoff
Create one compact multi-task recovery checkpoint. Do not implement, verify, review, close, commit, or change task authority.
Canonical usage:
$daily-handoff GAME-201 GAME-202 GAME-203 GAME-204
$daily-handoff
1. Resolve tasks exactly
- Use the current repository unless
--repoor--projectidentifies one exact path or unique repository name. Never guess between repositories. - Read repository
AGENTS.md,CLAUDE.md, their declared order, task/session conventions, and existingproduction/session-state/active.md. - Resolve each complete ID only as
production/tasks/<ID>/contract.mdand an explicit in-repositorycontract.mdpath directly. Preserve input order and deduplicate exact IDs. Never fall back to similarly named stories or partial IDs. - With no task arguments, use the same active-task selection as
task-status: lifecycle statein_progress,reopened,blocked, orready_to_closeplus tasks named by active orchestration. Do not include untouched ready backlog or closed tasks. - A missing or ambiguous task receives a
BLOCKEDhandoff section with the exact identity problem; it is not reinterpreted as prose.
2. Collect attributable evidence read-only
Read each contract's managed lifecycle block, implementation/verification/
bugfix handoffs, ownership/worktree ledgers, associated branch/base revision and
diff, retained verification artifacts, the complete managed defect ledger, and
Git/Plastic metadata. For a legacy
task without the block, read sibling status.md only as compatibility input;
never create, update, migrate, or delete it.
For every task report exactly:
Status: recorded lifecycle status and current phase, labeling inference;Completed work: only outcomes proven by a handoff, diff, or closure record; for defect work, include only rows with freshVERIFIEDevidence;Changed systems: contract area plus attributable paths/assemblies/assets;Verification evidence: check, result, source, revision, and freshness;Defects: unresolved and verified counts, stable IDs, linked-record integrity, and stale proof;Remaining blocker: one concrete blocker orNone;Next command: one short ID-first command or focused unblock action;Commit status:uncommitted,committed <revision>,none, orUNKNOWN.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago Changed · +2 lines afbfc6476ec2
- 29d ago First seen · 137 lines · 86 tokens per session scan A 6fa1ecfe4e9a
daily-handoff is a skill published in the GitHub repository furkantokkan/agent-foundry (11 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 1,390 once invoked, about $0.0003 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 2026-09-25.
Other skills, from other repositories
apex-status
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.
session-end
Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command.
session-start
Use this skill when initializing a session for any project repo. Autonomously analyzes git state, VCS issues, SSOT files, branches, environment, and cross-repo status. Then presents structured findings with recommendations before development wave planning, or an operations contract for explicitly requested…
close
End session with verification, commits, and documentation.
github-activity
Report what happened across GitHub repositories over a time window, read only. Invoke when the user asks what merged, which issues were opened or closed, or what moved between milestones since a date or since the last report, across one or more repositories.
implement-issue
Turn one labelled GitHub issue into one reviewed pull request, or stop with a stated reason. Use for every factory run; the message is a link to the issue.