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/donenpx skills add MissingPackage/nightshift --skill donegit 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 | $0.00065 | $0.00674 |
| Opus 5 | $0.00032 | $0.00337 |
| Sonnet 5 | $0.00013 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
done 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Definition of Done
Overview
Completion claims in this workspace follow one report shape. It exists because the user had to extract the same facts by hand after every change ("Hai fatto tutti i test? ... Cosa devo controllare io a mano? Come testo le modifiche?" — typed for five months).
A "done" without this report is not done. Fill every section; write "none" rather than omitting one.
The completion report (required shape)
## Done: <one-line what>
**Evidence** — commands actually run, with outcomes:
- unit: <command> → <result>
- integration: <command> → <result> (requires real services, e.g. Docker Compose)
- lint/format: <command> → <result>
- build/other gates: <...>
**Not verified** — what was NOT checked and why:
- <item — reason> (write "nothing" only if truly nothing)
**Your manual check** — what the user should verify by hand, and exactly how:
- <step-by-step, copy-pasteable>
**Conventions & docs** — project rules touched by this change:
- <e.g. domain events emitted for every new mutation? docs/ADR updated per project procedure? migrations?> → <status>
**Residue** — new issues noticed, out-of-scope, logged where:
- <item → Linear/docket ref, or "none">
Rules
- The report is written for the user, who often reads it on a phone: plain language, every project term explained in half a line or dropped, no bare sigla — docket items and phases are cited by their title, the ID at most in parentheses. Inside a goal loop, open with the trajectory line — objective was at X, is at Y, Z moves it next.
- Evidence means fresh output from this session, not "tests passed earlier" or "should pass".
- A gate you skipped, reported honestly under Not verified, is acceptable. A gate silently omitted is a false claim.
- Partial completion → say "Partially done", keep the same shape, list the remainder.
- Risk questions ("quanto rischio a pushare?") → answer with this report plus a one-line risk verdict grounded in the Not-verified section.
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 · 54 lines · 65 tokens per session scan A ca037ed7baa5
done is a skill published in the GitHub repository MissingPackage/nightshift (2 stars, last pushed 15d ago), licensed MIT. It adds 65 tokens to every session and 674 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).