claude-code-config: Skill for Claude Code

.claude/skills/pm-handoff/SKILL.md

pm-handoff is a skill for Claude Code from auerbachb/claude-code-config. It costs 96 tokens per session (7,750 once invoked), scanned A, original, MIT.

A handoff tool for moving project-management work from one coding-agent conversation to another. It collects project settings, current GitHub information, unfinished work, and a memory summary into a prompt for the new conversation.

In plain words
What is it for?
Use it when starting a new project-manager thread, changing context, or bootstrapping the project-management configuration; it can also copy the handoff text to the clipboard.
Why use it?
It prevents the next conversation from losing track of the repository, decisions, and work already in progress when the previous conversation runs out of context.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool; positional $N argument.

This is auerbachb/claude-code-config's own configuration. It tells Claude Code how to work on claude-code-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/skills/pm-handoff/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code.

Wrote 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.

agentmods badge for pm-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pm-handoff/github.svg)](https://agentmods.dev/skills/auerbachb/claude-code-config/pm-handoff)
Your own site
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/pm-handoff"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pm-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.

agentmods 80×15 button for pm-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/pm-handoff"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pm-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

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 →

  • high Rogue Agent · line 60
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Excessive Agency · line 256
    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.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.07750
Opus 5.5 $0.00038 $0.03100
Sonnet 5.5 $0.00019 $0.01550
Haiku 4.5 $0.00010 $0.00775

Measured 28d ago against content hash 770ee6600161, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pm-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 28d 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.

.claude/skills/pm-handoff/SKILL.md · 505 lines

How it starts

The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate a PM handoff prompt for starting or continuing a PM orchestration thread. This prompt is self-contained — paste it into a new Claude Code session (web or CLI) and the new thread becomes the project manager for this repo, with full awareness of what the previous PM thread was doing.

Resolve the config parser before Step 1:

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}
PM_CONFIG_GET_SH=$(resolve_script pm-config-get.sh || true)
[[ -n "$PM_CONFIG_GET_SH" ]] || { echo "ERROR: pm-config-get.sh not found (checked all three paths) — PM handoff config capture unavailable" >&2; exit 1; }

Parse $ARGUMENTS:

  • If $ARGUMENTS contains "copy" or "clipboard", copy the final output to clipboard via pbcopy in addition to stdout.
  • If empty, output to stdout only.

Step 1: Detect mode (bootstrap vs. standard)

Probe for the config file via the shared parser. pm-config-get.sh returns rc=2 for two distinct conditions it does not itself distinguish — "file missing" and "file exists but unreadable" (see its EXIT STATUS contract) — so disambiguate here with a plain existence check before dispatching. Skipping this check means a permissions glitch or transient filesystem issue on an existing config would be silently overwritten by Step 2's bootstrap.

CONFIG_FILE=".claude/pm-config.md"
"$PM_CONFIG_GET_SH" --list >/dev/null 2>&1
CONFIG_RC=$?

if [[ "$CONFIG_RC" -eq 0 || "$CONFIG_RC" -eq 1 ]]; then
  MODE="CONFIG_EXISTS"
elif [[ "$CONFIG_RC" -eq 2 && ! -e "$CONFIG_FILE" ]]; then
  MODE="BOOTSTRAP"
else
  MODE="UNREADABLE"
fi

CONFIG_RC 0 or 1 both mean the file was read successfully (1 just means zero sections or an empty section body — see the script's EXIT STATUS contract), so both map to CONFIG_EXISTS. Anything else — rc=2 with the file present, a usage error (rc=3), or any other unexpected exit code — maps to UNREADABLE rather than being silently treated as a healthy config.

  • If MODE == BOOTSTRAP (file genuinely absent): proceed to Step 2 (create config from repo scan)
  • If MODE == UNREADABLE (file exists but pm-config-get.sh returned an error for it, or returned an exit code outside the documented contract): STOP. Tell the user: ".claude/pm-config.md exists but could not be read — check file permissions and encoding before continuing." Do NOT proceed to Step 2 — bootstrapping here would silently overwrite the existing file's content, including any user-customized Role/OKRs/Team/Notes sections and any non-canonical sections.
  • Otherwise (CONFIG_EXISTS): skip to Step 3 (read existing config)

Read the full file on GitHub · 505 lines

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.

  1. 28d ago Changed 770ee6600161
  2. 29d ago Changed · +2 lines 32ea98c3b586
  3. 1mo ago Changed 2c88dc1e67ba
  4. 1mo ago Changed · +174 lines · +12 tokens per session 814faf83058b
  5. 2mo ago First seen · 329 lines · 84 tokens per session scan A 9b0ba58b45bd

Subscribe to this mod's changes

pm-handoff is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 7,750 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.