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 jazzyalex/agent-sessions --skill handovergit clone --depth 1 https://github.com/jazzyalex/agent-sessionsWrote 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/jazzyalex/agent-sessions/handover)<a href="https://agentmods.dev/skills/jazzyalex/agent-sessions/handover"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/handover/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/jazzyalex/agent-sessions/handover"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/handover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 63 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00071 | $0.00883 |
| Opus 5.5 | $0.00028 | $0.00353 |
| Sonnet 5.5 | $0.00014 | $0.00177 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
handover 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handover
Append a short, dated entry to RepoHandover.md at the repo root (newest-first)
capturing where things stand, so you or a future agent can resume. Keep it lean — a handful
of lines, no git audit. The user already opted in by running /handover, so draft and
write it directly — do NOT ask for approval or show a draft to confirm. Just write, report
one line, and stop. Never commit.
Procedure
-
Draft from the conversation — do NOT run a git audit. You already know what happened this session. At most, run a single
git branch --show-currentif you want the branch in the header. Do not rungit status/log/diffsweeps — that's the verbosity we removed. -
Compose a short entry in this format. Omit any line/section that would be empty. Aim for ~8–15 lines total:
## <YYYY-MM-DD HH:MM> · <slug> · <title> status: in-progress # in-progress | blocked | done **State:** <one sentence — where things stand right now> **Decided / don't redo:** <only if there is something> - <a decision made, or a dead-end already tried> **Key files:** <only if it helps resume> - `path` — <why it matters> **Next:** 1. <the next concrete step> 2. <...>slug= the branch or plan/spec name (keep it stable — supersede-matching uses it).- Timestamp:
date +'%Y-%m-%d %H:%M'.
-
Write it immediately — no approval prompt.
-
New file → create
RepoHandover.mdwith this entry as its only content. -
Existing file → prepend the entry above the current top entry (blank line between). Don't touch older entries except the silent supersede below.
-
Ensure the repo's
CLAUDE.mdcontains this pointer (add it once, creating a shortCLAUDE.mdif absent):> Before starting work, read the newest entry in `RepoHandover.md`. -
Silent supersede: if an older entry has the same
slugand its status isn't alreadydoneorsuperseded-by:, change that older entry's status line tostatus: superseded-by:<new-entry-date>(one-line edit; leave its prose alone). No prompt. -
Never run
git commit.
-
What ships with it
3 files 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.
- 1mo ago First seen · 68 lines · 71 tokens per session scan A f33554a87810
handover is a skill published in the GitHub repository jazzyalex/agent-sessions (909 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 883 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 2026-08-30.
Other skills, from other repositories
do-it-context
Use when project terms, relationships, or invariants drift between user language, docs, and implementation, or when stable project knowledge keeps being rediscovered or the user asks to document it.
studio-context-brief
Use when an active KIT-managed Goal needs compact brief, working, or resume context projections from trusted structured state while preserving exact technical literals and durable handoff authority.
codex-sdd:archive
Preserve change artifacts (proposal, design, tasks) into structured archive and update knowledge base. Final phase of OpenSpec workflow.
vibe-debugging-journal
Records resolved bugs in a persistent journal — symptom, root cause, difficulty, fix, prevention. Organized by category for future reference.
vibe-handover-doc
Generates a session continuity document at the end of a long session or when switching context on a multi-session project. Enables seamless resumption.
vibe-pattern-library
Detects recurring implementation patterns and records them for reuse. When the same code pattern appears 3+ times, it belongs in the pattern library.