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/assisjp/specflow/session-handoffnpx skills add assisjp/specflow --skill session-handoffgit clone --depth 1 https://github.com/assisjp/specflowWhat 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 | $0.00097 | $0.00729 |
| Opus 5 | $0.00048 | $0.00365 |
| Sonnet 5 | $0.00019 | $0.00146 |
| Haiku 4.5 | $0.00010 | $0.00073 |
Grade A, and why
session-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 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
Write an ephemeral handoff so a fresh agent can resume this work. The handoff is consumed once and then dies — it is session state, not a durable record.
Durable truth already has owners: architectural decisions live in ADRs, vocabulary in CONTEXT.md, requirements in the spec, verification commands in the block (AGENTS.md or CLAUDE.md), and tasks in the tracker. The handoff does not compete with any of them. State goes in the handoff; decisions go in an ADR.
Where it writes
Write to .scratch/handoffs/<short-slug>.md. First, guarantee .scratch/ is in .gitignore — if it is not, add it before writing. A handoff swept into a PR by the next spec-execution run is a leak, not a handoff.
What goes in it
Reference durable artifacts by path or URL — never duplicate a spec, ADR, or issue body. But a path only resolves if the receiving session sees the same version of the tree, so record the git state that pins it:
# Handoff — <one-line topic>
## Focus of the next session
<If the user passed an argument, this is it: what the next session should do.>
## Git state
- Branch: <branch>
- HEAD: <short SHA>
- Dirty files: <list, or "clean">
- Unpushed commits: <count, or "none">
## Where things stand
<2-6 lines of session state: what was being done, what is half-done, what
just broke. State, not decisions.>
## Artifacts (by reference, not copied)
- Spec: <path or issue URL>
- ADRs touched: <paths>
- Relevant files: <paths>
## Open threads
<What is unresolved and needs a decision or a next step.>
## Suggested skills
<Which skills the next session should invoke, e.g. `spec-execution <issue>`,
`grill` to resolve an open decision.>
Rules
- State, not decisions. A decision that will still matter months from now is an ADR, not a handoff line. If a handoff line records a why rather than a where things stand, it is a decision disguised as state — promote it to an ADR now (via
domain-modeling), do not carry it forward. - Reference, don't duplicate. Paths and URLs, pinned by the git state above. Copying content means it goes stale the moment the source changes.
- Redact secrets. No API keys, passwords, tokens, or PII in the handoff.
- Keep it short. A handoff nobody can read in a minute is one the next session skims and mistrusts.
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.
- 2d ago First seen · 57 lines · 97 tokens per session scan A 7b8594e28211
session-handoff is a skill published in the GitHub repository assisjp/specflow (17 stars, last pushed 23d ago), licensed MIT. It adds 97 tokens to every session and 729 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…