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.
git clone --depth 1 https://github.com/10Legs/freelance-developer-harnessWrote 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/commands/10legs/freelance-developer-harness/handoff-session)<a href="https://agentmods.dev/commands/10legs/freelance-developer-harness/handoff-session"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/handoff-session/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/commands/10legs/freelance-developer-harness/handoff-session"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/handoff-session.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 | $0.00023 | $0.00927 |
| Opus 5.5 | $0.00009 | $0.00371 |
| Sonnet 5.5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade B, and why
handoff-session scanned grade B 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 5d 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.
- `cat .claude/sessions/<SESSION_ID>.client 2>/dev/null || echo "(no client lock)"` — active client/project How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are generating a session handoff prompt. Goal: produce a single, self-contained prompt the user can paste into a brand-new Claude session so it knows exactly what we are working on — no stale context, no hallucination risk.
$ARGUMENTS may contain an optional focus note (e.g. "focus on the CI fix"). If present, bias the handoff toward that thread of work. If empty, cover the whole active session.
Step 1 — Probe real repo/env state (ground truth)
Run these via Bash from the harness root to anchor the handoff in facts, not memory. Use the SESSION_ID injected in the system prompt as SESSION_ID = <value> (fallback "default"):
cat .claude/sessions/<SESSION_ID>.client 2>/dev/null || echo "(no client lock)"— active client/projectgit branch --show-current— current branchgit status --short— uncommitted changesgit log --oneline -8— recent commits
If work this session touched a client source repo (a separate checkout outside the harness, per your multi-client convention), cd into it and run the same branch/status --short/log --oneline -5 there too. Determine the source repo path from the active client lock or from what was edited this session.
Step 2 — Synthesize from session context
From everything we did this session, extract:
- The actual task and goal — what we're building/fixing and why; current status; any open blocker.
- Critical files — the real paths we read/edited/created, each with a one-line purpose. Pull from the live session, do NOT invent paths. Cross-check against
git statusoutput. - Next steps — an ordered TODO of what the next session should do first. Be concrete.
- Decisions/constraints — any rule, gotcha, or decision made this session that the next session must not re-litigate.
Only include facts you are confident about. If unsure about something, mark it (unverified) rather than asserting it. Never fabricate file paths, branch names, or status.
Step 3 — Build the handoff prompt
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.
- 5d ago First seen · 73 lines · 23 tokens per session scan B 4b916bb41a81
handoff-session is a command published in the GitHub repository 10Legs/freelance-developer-harness (33 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 927 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other commands, from other repositories
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
init-workspace-flow-shells
Phase 2 Shells of init-workspace-flow.
sync
Session bootstrap - read project context, restore saved state, show status. Quick orientation with optional deep dive.
culture-onboarding-90
Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…
perf-difficult-conversation
Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…
perf-feedback-rehearsal
Rehearse a high-stakes feedback conversation before delivery. Takes an SBI sketch + recipient context, produces multiple openings, anticipated reactions with responses, SCARF-aware adjustments, and three branching paths the conversation could take with the manager's response to each. Saves to…