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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/plan-delete)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-delete"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-delete/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/oborchers/fractional-cto/plan-delete"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-delete.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 | $0.00027 | $0.01488 |
| Opus 5.5 | $0.00011 | $0.00595 |
| Sonnet 5.5 | $0.00005 | $0.00298 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade B, and why
plan-delete scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
TRANSCRIPT="$(find "$HOME/.claude/projects" -name "${SESSION_ID}.jsonl" -type f 2>/dev/null | head -1)" How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clear the current session's Claude Code plan file. Plans accumulate in ~/.claude/plans/<slug>.md as plan mode is re-entered within a session — this command resets to a clean slate.
Follow these steps exactly. Do not prompt the user for confirmation; the explicit /planning-tools:plan-delete invocation is the confirmation.
Step 1: Detect the current session's plan slug
Claude Code stamps every transcript entry with a top-level "slug" field once plan mode is entered. That slug equals the plan filename (without .md). This is the authoritative signal — far more reliable than path-grepping or file mtime.
Run this bash one-liner:
SESSION_ID="${CLAUDE_CODE_SESSION_ID:-}"
if [ -z "$SESSION_ID" ]; then
echo "ERROR: CLAUDE_CODE_SESSION_ID not set"; exit 1
fi
# Session IDs are globally unique UUIDs; find the transcript wherever it lives
# (more robust than computing the encoded-CWD path, which is fragile for paths with spaces/Unicode).
TRANSCRIPT="$(find "$HOME/.claude/projects" -name "${SESSION_ID}.jsonl" -type f 2>/dev/null | head -1)"
if [ -z "$TRANSCRIPT" ] || [ ! -f "$TRANSCRIPT" ]; then
echo "NO_TRANSCRIPT"; exit 0
fi
SLUG="$(grep -m1 -o '"slug":"[^"]*"' "$TRANSCRIPT" 2>/dev/null | sed 's/"slug":"//; s/"$//')"
if [ -z "$SLUG" ]; then
echo "NO_PLAN_FOUND"
else
# Defense in depth: slugs are random adjective-style strings like "moonlit-swimming-petal".
# Reject anything that could escape ~/.claude/plans/ (slashes, dots, control chars, spaces).
case "$SLUG" in
*[!a-z0-9-]*|""|*--*|-*|*-)
echo "ERROR: malformed slug rejected: '$SLUG'"; exit 1 ;;
esac
PLAN_PATH="$HOME/.claude/plans/${SLUG}.md"
echo "SLUG=$SLUG"
echo "PLAN_PATH=$PLAN_PATH"
ls -la "$PLAN_PATH" 2>/dev/null || echo "(file no longer exists on disk)"
fi
Interpret the output:
SLUG=<x>andPLAN_PATH=<path>→ go to Step 3NO_TRANSCRIPTorNO_PLAN_FOUND→ go to Step 2 (bootstrap)
Step 2: Bootstrap a plan file (only if Step 1 returned NO_PLAN_FOUND / NO_TRANSCRIPT)
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 · 105 lines · 27 tokens per session scan B b9e58b46c1ec
plan-delete is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 1,488 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 2026-10-13.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.