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 besoeasy/open-skills --skill project-agent-handoffgit clone --depth 1 https://github.com/besoeasy/open-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/besoeasy/open-skills/project-agent-handoff)<a href="https://agentmods.dev/skills/besoeasy/open-skills/project-agent-handoff"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/project-agent-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/besoeasy/open-skills/project-agent-handoff"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/project-agent-handoff.svg" alt="Reviewed on agentmods" width="80" 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 Excessive Agency · line 11 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00074 | $0.01305 |
| Opus 5 | $0.00037 | $0.00652 |
| Sonnet 5 | $0.00015 | $0.00261 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
project-agent-handoff 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 7d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Agent Handoff
Prepares a project for work by another AI coding agent: diagnose the current
state read-only, inventory architecture and safety gates, write or refresh
AGENTS.md, and verify the test suite. The goal is that any agent dropped
into the repo can operate correctly without asking the user basic questions
or touching dangerous code.
When to use
- The user says "help with " or "get up to speed on ".
- A repo is about to be opened by a different agent and has no (or stale)
AGENTS.md. - An agent previously failed or got confused working in a repo — use this to hand it a correct map.
Required tools
- A shell (bash) and the standard file tools of your agent runtime.
- No external APIs required. All steps are local and read-only except the
explicit test run and the
AGENTS.mdwrite.
Workflow
1. Diagnose first (read-only)
Run these and record results before proposing any change:
# Running processes / sessions related to the app
ps aux | grep -Ei "python|node|engine|watchdog" | grep -v grep
tmux ls 2>/dev/null # long-running app sessions
uptime && date -u # reboot? note timezone vs UTC logs
# Runtime state files (adjust names to the project)
ls -lat data/ 2>/dev/null | head -20
cat data/live_status.json 2>/dev/null # or equivalent status/state files
tail -30 logs/*.log 2>/dev/null # recent errors
Key discipline:
- Logs often use UTC while the shell shows local time. Convert before
concluding a service is "stale" (e.g.
date -u). - Check what stdout a live process points at:
ls -l /proc/<pid>/fd/1— tmux/systemd redirection hides real output. - Never conclude a bug from one log line; count occurrences
(
grep -c "PATTERN" log) and read the surrounding events.
2. Inventory the architecture
- List entry points:
ls *.py *.sh/cat package.json/cat Cargo.toml. - Identify anything that moves money, sends messages, or mutates prod: mark these as safety gates that any agent must respect.
- Identify config: where secrets live (
.env, env vars), how modes are switched (paper vs live vs testnet).
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.
- 7d ago First seen · 131 lines · 74 tokens per session scan A 668f243b1448
project-agent-handoff is a skill published in the GitHub repository besoeasy/open-skills (132 stars, last pushed 7d ago), licensed MIT. It adds 74 tokens to every session and 1,305 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
ax-agent-rlm
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…
new-app
Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.