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 nmamano/isomux --skill isomux-handoffgit clone --depth 1 https://github.com/nmamano/isomuxWrote 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/nmamano/isomux/isomux-handoff)<a href="https://agentmods.dev/skills/nmamano/isomux/isomux-handoff"><img src="https://agentmods.dev/badge/skills/nmamano/isomux/isomux-handoff.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 48 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00051 | $0.00555 |
| Opus 5 | $0.00026 | $0.00278 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
isomux-handoff 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 8d 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.
curl -s -X POST localhost:4000/api/agents/<your-own-id>/handoff \ How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue your unfinished task on a fresh session. Use this when your context is getting full but the work isn't done: you distil what's LEFT (not what happened) into a brief and hand off to a fresh copy of yourself that resumes on just that brief.
1. Write the handoff brief
The brief is FORWARD-LOOKING: only what the next session needs to carry the work forward. It is NOT a summary of this conversation.
Include:
- The goal: what still needs to be accomplished, as concretely as you can.
- The next concrete steps: what you'd do next if you kept going.
- Working state that isn't obvious from disk: dirty files, active worktrees/branches, paths, commits, anything uncommitted, in-flight commands.
- Decisions already made that the fresh session shouldn't relitigate, and any open questions or unconfirmed assumptions to revisit with the boss.
- Pointers: the specific files, docs, or task IDs the work touches.
Deliberately leave OUT:
- A narrative recap of what happened this session ("first I did X, then Y...").
- Anything already in your system prompt, your custom instructions, or isomux memory. The fresh session reloads all of that automatically.
- Generic advice the fresh you would already know.
Keep it tight.
2. Get the boss's approval
Show the boss the exact brief you intend to hand off and wait for their confirmation.
3. Hand off
Hand off to a fresh copy of yourself with the approved brief. This resets your session and delivers the brief into the fresh session in one step, so a clean copy resumes on the brief - instantly, with no wait:
curl -s -X POST localhost:4000/api/agents/<your-own-id>/handoff \
-H "Authorization: Bearer $ISOMUX_AGENT_TOKEN" \
-H 'Content-Type: application/json' \
-d '{"text":"<the approved brief>"}'
Your current turn ends as the reset takes effect; the fresh session picks up the
brief on its own. (For a genuine FUTURE reminder or wake-up instead of an
immediate handoff, use the scheduled-message path - a POST to your own
/messages with a deliverAt - rather than this endpoint.)
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.
- 8d ago First seen · 58 lines · 51 tokens per session scan A 9bdafc8b4668
isomux-handoff is a skill published in the GitHub repository nmamano/isomux (37 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 555 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 2026-08-30.
Other skills, from other repositories
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
cog-onboarding
Personalize COG Second Brain workflow through role pack selection and vault initialization.
cog-weekly-reflection
Cross-domain pattern analysis with personal, professional, and project domain synthesis.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.