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 isvlasov/rageatc-oss --skill handovergit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/handover)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/handover"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/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/isvlasov/rageatc-oss/handover"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/handover.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 | $0.00045 | $0.00683 |
| Opus 5 | $0.00023 | $0.00342 |
| Sonnet 5 | $0.00009 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00068 |
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 9d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handover (Write State)
Update project files so the next session can pick up exactly where this one left off.
Step 1: Review the session
Before touching any files, reflect: what was created or significantly changed? What decisions were made? What was discovered or learned? Were new key files created (e.g. in work/) that a fresh session would need to know about?
Step 2: Update root files
Check every .md file in the project root. Follow each file's own update instructions (found at the top of the file); if a file has none, update it whenever this session's work has made it stale.
Common root files and their update logic:
| File | How to update |
|---|---|
| STATUS.md | Rewrite with current state (current position, recent decisions, next steps, open questions) |
| LEARNINGS.md | Append only what passes the file's inclusion criteria — a durable insight a future session would act on. Most sessions add nothing. Do NOT use as a session log. |
| BACKLOG.md | Move new granular tasks or unresolved issues here. Keep STATUS.md "next steps" focused only on immediate session continuity. |
| CLAUDE.md | Update pointers — add new key files, remove stale pointers, update descriptions |
| README.md | Update if project description, status, or structure changed |
| PRD.md | Update if requirements shifted |
| ARCHITECTURE.md | Update if architectural decisions changed |
| ROADMAP.md | Update if chunks were completed, added, or reordered |
| ORCHESTRATION-PLAN.md | Mark completed chunks, update build progress |
Not every project has all of these. Check what exists.
Step 3: Follow CLAUDE.md pointers
For each file CLAUDE.md references beyond the root (e.g. work/ artefacts, orchestration logs): does the pointer still point to the right location? Has this session's work made the file stale? Update if needed.
Step 4: Hygiene checks
Structural checks only — don't deep-read files.
- CLAUDE.md compliance — lean pointer file standard: one-line project identity; points to key files without absorbing their content; no embedded architecture, requirements, status, or workflow descriptions; no stale sections duplicating files it points to. Fix non-compliance now.
- Dangling pointers — every file path referenced in CLAUDE.md and STATUS.md exists. Flag broken references to the user — don't silently remove; the file may have been moved.
- Git hygiene — run
git status: junk files (.DS_Store,*.swp,__pycache__/,.pyc) → add to.gitignore; untracked files that don't look like this session's work → flag to the user, don't delete.
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.
- 9d ago First seen · 49 lines · 45 tokens per session scan A 89a1812f69b6
handover is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 683 once invoked, about $0.0002 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
memory-review
Review the file-based memory store via the Agent Monitor Config Explorer API: the user and project CLAUDE.md plus per-project auto-memory files under /.claude/projects/ /memory/.md. Groups by project, shows the index (MEMORY.md) vs per-fact files, and flags stale or oversized facts. Reads /api/cc-config/memory and…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
context-anchoring
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…
learning-harvest
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes…
knowledge-priming-refiner
Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create…