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 jasonm4130/claude-skills --skill handoffgit clone --depth 1 https://github.com/jasonm4130/claude-skillsWrote 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/jasonm4130/claude-skills/handoff)<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/handoff"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/handoff/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/jasonm4130/claude-skills/handoff"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/handoff.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 | $0.00130 | $0.01344 |
| Opus 5 | $0.00065 | $0.00672 |
| Sonnet 5 | $0.00026 | $0.00269 |
| Haiku 4.5 | $0.00013 | $0.00134 |
Grade B, and why
handoff scanned grade B with 2 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
the user can manually `cat .claude/handoffs/<filename>` to prime the next session. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`if (res.status === 401) { await refreshAccessToken(); return fetch(req); }` How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a structured resume document that lets the next Claude session understand exactly where this session left off — without needing any of this conversation's context.
Accept an optional free-form <focus> argument. If provided, use it as the
slug (lowercased, spaces replaced with hyphens). If omitted, slug = auto.
Output location
$PROJECT_ROOT/.claude/handoffs/<ISO-timestamp>-<slug>.md
For example:
/handoff auth-token-bug→.claude/handoffs/2026-05-25T14-32-00-auth-token-bug.md/handoff→.claude/handoffs/2026-05-25T14-32-00-auto.md
Create the .claude/handoffs/ directory if it doesn't exist. It should be
gitignored — add /.claude/handoffs/ to .gitignore if not already present.
Required sections
Write these sections in order. Keep each section tight.
Current state
1-2 sentences. Where are we right now? What's working, what's half-done?
What we tried (MOST IMPORTANT)
Bullet list of failed/abandoned approaches and why each failed. This is the highest-value section — the next session must not re-attempt the same dead ends. If nothing failed, write "Nothing failed — clean path to current state."
Key decisions
Each decision on its own line: Decision — why. No orphan decisions without a reason.
Modified files
Table or list: file path + one-line note on what changed and why. Be concrete
(src/auth/token.ts — added 24h expiry check, not "changed auth file").
Blockers
Anything that is genuinely blocked and why. If none, write "None."
Next concrete step
A single runnable instruction. Must be one of:
- A bash command:
npm test -- auth.test.ts - A file+line:
src/auth/token.ts:142 — implement the refresh logic - A numbered list if the next step has 2-3 substeps
NOT acceptable: "continue the refactor", "pick up where we left off", "keep going with the auth work".
Worked example
## Current state
Token refresh is half-implemented. The request path works but the 401-retry
loop in `fetchWithAuth` is not wired up yet.
## What we tried
- Tried intercepting at the axios level (src/api/client.ts) — abandoned
because interceptors run before the token check, causing double-refresh.
- Tried a global event bus approach — too complex, reverted in commit a3f9d2.
## Key decisions
- **Store refresh token in httpOnly cookie** — avoids XSS exposure via
localStorage (OWASP TOP-10 A02).
- **Retry once on 401, then force logout** — prevents infinite loops on
revoked tokens.
## Modified files
- `src/auth/token.ts` — added `refreshAccessToken()`, wires to cookie store
- `src/api/fetchWithAuth.ts` — placeholder for retry logic (TODO at line 58)
- `tests/auth.test.ts` — added 3 token-refresh scenarios, all currently skipped
## Blockers
- `refreshAccessToken()` needs the backend `/auth/refresh` endpoint, which
isn't deployed yet. Ticket: JIRA-4821.
## Next concrete step
Open `src/api/fetchWithAuth.ts:58`, implement the retry wrapper:
`if (res.status === 401) { await refreshAccessToken(); return fetch(req); }`
Then run: `npm test -- --testPathPattern auth`
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.
- 12d ago First seen · 138 lines · 130 tokens per session scan B f3cbad91caba
handoff is a skill published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 130 tokens to every session and 1,344 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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.
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
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…