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/missingpackage/nightshift/handoffnpx skills add MissingPackage/nightshift --skill handoffgit clone --depth 1 https://github.com/MissingPackage/nightshiftWhat 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 | $0.00063 | $0.00731 |
| Opus 5 | $0.00032 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Hand-off
Overview
Project state must survive the session. This skill replaces hand-transplanting context between sessions ("In un'altra sessione claude ha identificato…") and re-deriving it after crashes.
The artifact is HANDOFF.md at the project root (or research/AGENDA.md where that convention already exists — never both).
On session start (project has HANDOFF.md / AGENDA.md)
Read it BEFORE exploring. Trust its "next decidable" unless the repo contradicts it — if it does, say so and update it: a stale hand-off is worse than none.
On session end (state changed)
Refresh — do not append-only — HANDOFF.md as a map (form adopted 2026-08-12, ruling
"verbale del disegno workflow", from wayfinder's shared-map idea):
# HANDOFF — <project> (updated <date>)
## 1. Next decidable
The single next action, with enough context to re-enter cold in five minutes —
this stays FIRST: it is what session-anchor injects and what a fresh /loop
session re-anchors on. If everything is user-gated: say so, list the open
decisions by TITLE.
## 2. Map
- **Destination**: the goal objective in 1-2 lines, and the distance from it NOW
(the trajectory line).
- **Decisions so far**: an index — one line per decision, title + where it lives
(docket path). Gist and link, never restate: a decision lives in exactly one place.
- **Fog**: what is not yet specified — the known unknowns, so scope emerges here
instead of leaking into work.
- **Out of scope**: deliberately excluded, so it stops being re-proposed.
## 3. Landmines
- things the next session must NOT do / must know (broken invariants,
half-applied patterns, env quirks discovered)
Keep it under 80 lines — the Stop hook handoff-freshness now warns beyond that.
It is a re-entry document, not a journal: narrative history lives in digests.md
(append-only, one entry per cycle), decisions live in the docket, technical trace
in the journal. Older material moves there or gets deleted — section 1 is the
contract, history is not. Write PI-facing files with the Edit tool, not shell
heredocs: the user may read them on a phone, where they render as app diffs.
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.
- yesterday First seen · 63 lines · 63 tokens per session scan A ff389f32bfa0
handoff is a skill published in the GitHub repository MissingPackage/nightshift (2 stars, last pushed 15d ago), licensed MIT. It adds 63 tokens to every session and 731 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
baton-setup
One-time setup and health check for fable-baton. Use when the user asks to set up, configure, verify, or troubleshoot fable-baton - sets the default model to "best" (Fable 5 with Opus fallback) in /.claude/settings.json and verifies the plugin is fully installed.
licensing-tiers-data-governance
Implement subscription tiers with field-level access control, feature gating, rate limiting, and compliance tracking. Design data governance systems that enforce different access levels, retention policies, and regulatory requirements based on user subscription tier (Free, Pro, Enterprise).
data-infrastructure-at-scale
Build data infrastructure that scales from prototype to production. Use when architecting data pipelines, choosing data stores, planning for high throughput, or migrating to distributed systems. Covers caching, replication, sharding, message queues, and data lake architecture.
data-provenance
Track data lineage and provenance from source to consumption. Use when auditing data flows, debugging data quality issues, ensuring compliance (GDPR, SOX), or understanding data dependencies. Covers lineage tracking, impact analysis, data catalogs, and metadata management.
multi-source-data-conflation
Merge and reconcile data from multiple sources into a unified view. Use when integrating APIs, consolidating databases, building data warehouses, or creating master data. Covers entity resolution, conflict resolution, data quality, and real-time vs batch conflation.
software-architecture
Design scalable software systems with proven architectural patterns (MVC, microservices, event-driven), SOLID principles, system design trade-offs, and architectural decision records (ADRs).