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/backspace-shmackspace/claude-devkit/auditnpx skills add backspace-shmackspace/claude-devkit --skill auditgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.00011 | $0.05506 |
| Opus 5 | $0.00005 | $0.02753 |
| Sonnet 5 | $0.00002 | $0.01101 |
| Haiku 4.5 | $0.00001 | $0.00551 |
Grade A, and why
audit 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 — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit Workflow
Inputs
- Scope: $ARGUMENTS (optional: "plan", "code", "full")
plan: Audit a plan file before implementationcode: Audit recent uncommitted changes (default)full: Full codebase scan
Output Rules
- Always print full absolute paths for all artifact references (plan files, review files, audit logs). This makes paths clickable in terminals like Warp. Use the resolved
$PLANS_DIRvalue, never relative paths.
Role
You are the audit coordinator. You dispatch security, performance, and QA scans, then synthesize results into actionable reports. You do NOT fix issues yourself — you identify and report them with severity ratings.
Step 1 — Determine scope
Resolve devkit paths (MUST be first action in Step 1):
Tool: Bash
# --- Devkit Path Resolution ---
DEVKIT_SCRIPTS="${CLAUDE_DEVKIT:-$HOME/.claude-devkit}/scripts"
# Source path resolution helper
if [ -f "$DEVKIT_SCRIPTS/resolve-project-dir.sh" ]; then
. "$DEVKIT_SCRIPTS/resolve-project-dir.sh"
DEVKIT_PROJECT_DIR_RESOLVED=$(resolve_devkit_project_dir) || {
echo "Failed to resolve project directory" >&2; exit 1
}
elif [ -n "${DEVKIT_PROJECT_DIR:-}" ]; then
DEVKIT_PROJECT_DIR_RESOLVED="$DEVKIT_PROJECT_DIR"
else
echo "WARNING: devkit is not installed. Using deprecated .devkit/ fallback." >&2
DEVKIT_PROJECT_DIR_RESOLVED=".devkit"
fi
PLANS_DIR="$DEVKIT_PROJECT_DIR_RESOLVED/plans"
mkdir -p "$PLANS_DIR"
echo "Plans directory: $PLANS_DIR"
Tool: Bash (direct — coordinator does this)
Run: git status --porcelain
Scope resolution:
- If
$ARGUMENTSis empty:- If git status shows uncommitted changes: scope = "code"
- Else: scope = "full"
- Else: scope =
$ARGUMENTS
Validate scope is one of: plan, code, full. If not, stop with:
"Invalid scope. Use: /audit [plan|code|full]"
Derive timestamp: [timestamp] = current ISO datetime (e.g., 2026-02-07T12-30-00)
Initialize audit logging:
Tool: Bash
# --- Audit Logging Setup ---
RUN_ID=$(date +%Y%m%d-%H%M%S)-$(cat /dev/urandom | LC_ALL=C tr -dc 'a-z0-9' | head -c 6)
AUDIT_LOG_DIR="$PLANS_DIR/audit-logs"
mkdir -p "$AUDIT_LOG_DIR"
AUDIT_LOG="$AUDIT_LOG_DIR/audit-${RUN_ID}.jsonl"
STATE_FILE=".audit-audit-state-${RUN_ID}.json"
python3 -c "
import json
state = {
'run_id': '${RUN_ID}',
'audit_log': '${AUDIT_LOG}',
'skill': 'audit',
'skill_version': '3.3.0',
'security_maturity': 'advisory',
'hmac_key': ''
}
with open('${STATE_FILE}', 'w') as f:
json.dump(state, f)
print('Audit skill state file created: ${STATE_FILE}')
"
bash "$DEVKIT_SCRIPTS/emit-audit-event.sh" "$STATE_FILE" \
"{\"event_type\":\"run_start\",\"scope\":\"${AUDIT_SCOPE:-unknown}\"}"
bash "$DEVKIT_SCRIPTS/emit-audit-event.sh" "$STATE_FILE" \
'{"event_type":"step_start","step":"step_1_determine_scope","step_name":"Determine scope","agent_type":"coordinator"}'
echo "Audit skill log: $AUDIT_LOG"
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 · 580 lines · 11 tokens per session scan A a37b58a87f10
audit is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 8d ago), licensed MIT. It adds 11 tokens to every session and 5,506 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-feature-coordinator
L1 feature coordinator - drives approved ROADMAP.md lanes through their required build/review/verification gates and owns the run-wide feature frontier.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.