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 agentmods add skills/auerbachb/claude-code-config/pm-updatenpx skills add auerbachb/claude-code-config --skill pm-updategit clone --depth 1 https://github.com/auerbachb/claude-code-configWhat 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 | $0.00101 | $0.04073 |
| Opus 5 | $0.00051 | $0.02037 |
| Sonnet 5 | $0.00020 | $0.00815 |
| Haiku 4.5 | $0.00010 | $0.00407 |
Grade A, and why
pm-update 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 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.
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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Re-scan the current repo and update .claude/pm-config.md, then sweep stale worktrees and branches. Auto-generated config sections (Infrastructure, Architecture) are regenerated from the repo's current state; user-edited sections are preserved verbatim. After the config write, the stale-cleanup pass surfaces (and optionally removes) worktrees and branches that have aged past the threshold.
Resolve the parser and cleanup helper 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=$(resolve_script pm-config-get.sh || true)
STALE_CLEANUP_SH=$(resolve_script stale-cleanup.sh || true)
[[ -n "$PM_CONFIG_GET_SH" ]] || { echo "ERROR: pm-config-get.sh not found (checked all three paths) — PM config preservation unavailable" >&2; exit 1; }
[[ -n "$STALE_CLEANUP_SH" ]] || { echo "ERROR: stale-cleanup.sh not found (checked all three paths) — workspace cleanup unavailable" >&2; exit 1; }
Section classification
| Section | Type | Behavior on update |
|---|---|---|
| Role | User-edited | Preserved verbatim |
| OKRs | User-edited | Preserved verbatim |
| Workflow Rules | User-edited | Preserved verbatim |
| Dependency Rules | User-edited | Preserved verbatim |
| Team | User-edited | Preserved verbatim |
| Notes | User-edited | Preserved verbatim |
| Infrastructure | Auto-generated | Regenerated from repo scan |
| Architecture | Auto-generated | Regenerated from repo scan |
| Any other section name | Non-canonical | Preserved verbatim, repositioned next to its nearest canonical neighbor (see Step 6) |
Step 1: Verify config exists
test -f .claude/pm-config.md || echo "NO_CONFIG"
If .claude/pm-config.md does not exist, tell the user: "No PM config found. Run /pm first to bootstrap it." Then stop.
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 · 249 lines · 101 tokens per session scan A 795ae25d4bdf
pm-update is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 4,073 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
jira
Unified Jira entry point. Routes to preview (default), create, or review subcommands.
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.
standup
Generate standup summary from git history, track progress, and Jira/GitHub activity. Read-only — makes no changes to the codebase.
status
Display current progress of Draft tracks and active tasks. Shows phases, completion percentages, and blocked items.
workspace-status
Use this skill to orient at session start, check initiative queue state, or see what's ready to work on next. Reads workspace.toml and surfaces ready-to-start items, blocked items with reason, parallel candidates, and active signals. Triggers on "workspace status", "where am I", "orient me", "session start", "what's…
impact
Generate a project-wide impact report on Draft track delivery — pace, phase duration, completion rate, friction hotspots, ADR/guardrail/decomposition adoption — by parsing track metadata, git revert history, and phase timestamps. Use when measuring CDD effectiveness ("show project impact", "where are bottlenecks"…