A session-resume procedure for restoring saved information from an earlier coding-agent conversation. It uses a handoff token or searches for a matching saved handoff.

Use it when continuing earlier work, loading a handoff token, choosing among saved sessions, or checking whether a previous handoff is still available.

It prevents resumed work from starting without the previous task’s context, decisions, and progress.

sw-load — Skill by nomadop

Install

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.

agentmods

npx agentmods add skills/nomadop/session-watcher/sw-load

Any agent

npx skills add nomadop/session-watcher --skill sw-load

Clone the repo

git clone --depth 1 https://github.com/nomadop/session-watcher

Made for: Claude Code, Codex.

Or install session-watcher, the plugin that ships this one along with the rest of its 3 skills, 1 hook.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 715 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00052	$0.00715
Opus 5	$0.00026	$0.00358
Sonnet 5	$0.00010	$0.00143
Haiku 4.5	$0.00005	$0.00072

Measured 2d ago against content hash 625ea3bbf931, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sw-load scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Fallback (MCP unavailable or returns error): resolve the server URL from session-start additionalContext (`Session Watcher server: http://...`) or latest state file in `~/.session-watcher/`, then use `curl -s '<url>/api/

skills/sw-load/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Watcher Load Handoff

Restore a previous session's handoff package into context so work can resume.

Steps

Resolve the token — check these sources in order:
- Skill args (if invoked with a token directly).
- The user's message (e.g. handoff：some-token-here).
- System-reminder containing [Session Watcher] Handoff available (token: <token>, ...) — extract the token from that line.
Load the handoff via MCP load_handoff tool:
- Token known (single): call load_handoff with load_token → proceed directly.
- Multiple tokens in system-reminder: list them with age/task preview, ask the user which to load.
- Query search: call load_handoff with query → present results, user picks.
- Auto-match: call load_handoff with no args → present what was found, user confirms before proceeding.
Only the token-known path skips user confirmation — query and auto-match always require the user to confirm which handoff to load. If found: false → inform user the token is expired/invalid, ask for direction.

Fallback (MCP unavailable or returns error): resolve the server URL from session-start additionalContext (Session Watcher server: http://...) or latest state file in ~/.session-watcher/, then use curl -s '<url>/api/handoff/load?load_token=<token>'.
Read kept paths — you MUST see PATHS.md for resolution and read-strategy rules.
Orient via bookmarks — if bookmark_index / recent_user_intents present in the load response:
- Scan bookmark_index for the work trajectory (what was being built/fixed)
- Scan recent_user_intents for the user's actual asks
- If a bookmark looks critical but the summary doesn't cover it: call get_bookmark_detail with that turn_index for ±3 turn context
- Don't drill every bookmark — only when the summary leaves a gap
Load skills — if skills_to_keep present, invoke each via the Skill tool.
Present loaded context to user:
- Objective (1 line)
- Working state (from what you actually read — confirm or correct the summary's claims)
- Next task + entry points
- Blockers/risks

Read the full file on GitHub · 53 lines

Files

What ships with it

1 file 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.

PATHS.md 1.6 KB

Changes

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.

2d ago First seen · 53 lines · 52 tokens per session scan A 625ea3bbf931

Subscribe to this mod's changes

sw-load is a skill published in the GitHub repository nomadop/session-watcher (3 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 715 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cost Optimization Memory and context coding-agents dashboard developer-tools eoq mcp-server

dvalin-security-scan

Scan code for injection, hardcoded secrets, XSS, dynamic code execution, and unsafe shell use. Use after writing or modifying code that handles user input, builds queries or commands, touches authentication, or adds a dependency — and whenever the user asks for a security check, audit, or review. Runs locally with no…

arthurpanhku/dvalincode · 77 tokens

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

griddynamics/rosetta · 32 tokens

c-03-repo-bootstrap

Bootstrap onboarding for undocumented repos or existing memory slices. Builds root overviews, route-local overview pillars, evidence packs, file cards, onboarding waves, deleted-slice cleanup, curator reviews, and handoff while keeping the orchestrator thin.

Foxfire1st/agents-remember · 54 tokens

c-12-closeout

Close out approved Agents Remember edits by preserving approval authority, mandatory strict code quality before code commit, missing-onboarding checks, external-memory refresh, memory quality, ledger alignment, and no automatic push.

Foxfire1st/agents-remember · 45 tokens

l-01-agent-lifecycles

The agent lifecycles: one lifecycle per agent type, under one roof. Routes every session by exactly three conditions (spawn-role env -> fresh role brief -> otherwise free-chat launcher), carries the minimal lifecycle frame (the six lifecycle signals every session shares), and houses the self-contained per-role…

Foxfire1st/agents-remember · 135 tokens

c-09-git-worktree-manager

Create, attach to, report on, integrate, finalize, and clean up Agents Remember worktree-backed tasks while preserving delegated/human approval gates and external-memory compatibility.

Foxfire1st/agents-remember · 42 tokens

sw-load