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 pantheon-org/tekhne --skill handover-document-creatorgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/handover-document-creator)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/handover-document-creator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/handover-document-creator/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/pantheon-org/tekhne/handover-document-creator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/handover-document-creator.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 | $0.00163 | $0.02516 |
| Opus 5.5 | $0.00065 | $0.01006 |
| Sonnet 5.5 | $0.00033 | $0.00503 |
| Haiku 4.5 | $0.00016 | $0.00252 |
Grade A, and why
handover-document-creator 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 10d 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.
Handover Document Creator
Write (or pick up) a session handover: a point-in-time snapshot of what happened and what remains outstanding, filed under .context/handovers/ so a different agent or a future session of the same
agent can resume the work cold, without needing this conversation's context.
When to use
- The session is ending (context limit approaching, user stepping away,
/clearabout to happen) and meaningful work is still in progress - The user explicitly asks for a handover, a "what's outstanding" summary for someone else, or to "hand this off"
- Work is moving between worktrees, branches, or agents (e.g. a wave-based parallel implementation, or handing a spike off to a colleague's session)
When not to use
- The session's work is fully complete and nothing is outstanding: no handover is needed, the git history and any
.context/follow-ups/entries already filed are sufficient - A single outstanding item with no broader session context: file it as a
.context/follow-ups/entry via thecreate-context-fileskill instead (see Relationship to other typologies below) rather than writing a whole handover for one item - Journal entries, tool assessments, or plan documents already cover the need: don't duplicate this skill's job into those, or vice versa
Directory and naming convention
.context/handovers/
YYYY-MM-DD-<slug>.md
One dated file per handover, following the same YYYY-MM-DD-<slug>.md convention as .context/follow-ups/ and .context/plans/. A handover is a snapshot, not a living document: a second handover on
the same topic is a new dated file with supersedes set, never an in-place edit of the first. Why, and how this differs from tool-review-assessment's in-place convention:
references/typology-and-lifecycle.md.
Frontmatter (required)
---
title: "TICKET-123 example-service dev rollout - mid-migration"
type: handover
date: 2026-09-08 # ISO date (YYYY-MM-DD), must match the filename's date segment
branch: feat/ticket-123-example-service-dev
status: active # active | done | superseded
---
What ships with it
23 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.
- .audits/2026-10-02/Analysis.md 558 B
- .audits/2026-10-02/audit.json 704 B
- .audits/2026-10-02/Remediation.md 1.5 KB
- .audits/2026-10-07/Analysis.md 558 B
- .audits/2026-10-07/audit.json 704 B
- .audits/2026-10-07/Remediation.md 1.5 KB
- assets/schemas/handover-frontmatter.schema.json 3.3 KB
- assets/templates/handover.yaml 5.6 KB
- CHANGELOG.md 1.8 KB
- evals/instructions.json 5.0 KB
- evals/scenario-1/capability.txt 158 B
- evals/scenario-1/criteria.json 2.4 KB
- evals/scenario-1/task.md 3.0 KB
- evals/scenario-2/capability.txt 155 B
- evals/scenario-2/criteria.json 1.9 KB
- evals/scenario-2/task.md 2.8 KB
- evals/scenario-3/capability.txt 186 B
- evals/scenario-3/criteria.json 2.0 KB
- evals/scenario-3/task.md 2.5 KB
- evals/summary.json 731 B
- references/document-structure.md 2.7 KB
- references/typology-and-lifecycle.md 2.7 KB
- scripts/validate-handover.sh 3.7 KB runs code
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.
- 10d ago Changed · +2 lines 81d31a575632
- 19d ago First seen · 137 lines · 163 tokens per session scan A 23101990e65b
handover-document-creator is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 2,516 once invoked, about $0.0007 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 2026-09-29.
Other skills, from other repositories
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
factory-collect
Experimental workflow for collecting and triaging product feedback, product telemetry, runtime errors, and issue reports. Use when scanning configured signal sources and applying separate fix, reply, or close rules.
factory-human-digest
Experimental workflow for summarizing work that still needs human judgment across configured pull requests, issues, feedback, errors, and delivery signals. Use for a human decision queue or bounded review.
factory
Experimental workflow for configuring an autonomous software delivery factory. Use when choosing feedback sources, schedules, worktree behavior, autonomy gates, or host automations.
factory-recover
Experimental workflow for finding and resuming interrupted coding runs. Use after an agent host restart or an interrupted automation.