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 commands/sanmak/specops/resume-plangit clone --depth 1 https://github.com/sanmak/specopsWrote 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/sanmak/specops/resume-plan)<a href="https://agentmods.dev/commands/sanmak/specops/resume-plan"><img src="https://agentmods.dev/badge/commands/sanmak/specops/resume-plan.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01779 |
| Opus 5 | $0.00000 | $0.00890 |
| Sonnet 5 | $0.00000 | $0.00356 |
| Haiku 4.5 | $0.00000 | $0.00178 |
Grade A, and why
resume-plan 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 4d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume a previously created plan — discovers plan files, syncs with latest main, and presents the plan ready for implementation.
Instructions
Follow these steps precisely.
Argument Parsing
Parse $ARGUMENTS:
- If non-empty, treat as a plan file identifier: a full filename (e.g.,
serene-hugging-orbit.md), a name without extension (e.g.,serene-hugging-orbit), or a full path. - If empty, proceed to plan discovery in Step 1.
Step 1: Discover and select plan file
If $ARGUMENTS is empty:
- List all
.mdfiles in~/.claude/plans/sorted by modification time (newest first):ls -t ~/.claude/plans/*.md 2>/dev/null - If no files are found, report "No plan files found in
~/.claude/plans/. Create a plan using Claude Code's plan mode first." and stop. - For each plan file (limit to the 15 most recent), extract:
- The filename (without path)
- The modification date:
stat -f '%Sm' -t '%Y-%m-%d %H:%M' <file>(macOS) orstat -c '%y' <file>(Linux) - The first
#heading from the file content, or "Untitled plan" if none
- Display the list as a numbered table:
Available plans (most recent first):
# Plan file Last modified Title
1 serene-hugging-orbit.md 2025-03-18 23:14 Plan: Resolve PR #56 Conflicts
2 majestic-knitting-haven.md 2025-03-17 14:22 Plan: Update README
...
- Ask the user: "Which plan would you like to resume? Enter a number or filename." Wait for their response. Save the selection as
PLAN_PATH.
If $ARGUMENTS is non-empty:
- If
$ARGUMENTSis a full path:- Reject if it is outside
~/.claude/plans/unless the user explicitly confirms. - Require
.mdextension. - If valid and the file exists, save as
PLAN_PATH; otherwise report an error and stop.
- Reject if it is outside
- If
$ARGUMENTSis a filename (with or without.md), look for it in~/.claude/plans/. Append.mdif not already present. If found, save asPLAN_PATH. - If the file is not found, report "Plan file not found:
$ARGUMENTS. Run/resume-planwithout arguments to list available plans." and 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.
- 4d ago First seen · 142 lines · 0 tokens per session scan A 09c75bbcd697
resume-plan is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,779 tokens. 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 commands, from other repositories
modernization-flow-grouping
Phase 4 Class Grouping of modernization-flow.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
security-flow-authorize
Phase 2 Authorize of security-flow.
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
nuke
You are the Nuke Commander: a disciplined destructive operations agent that ensures safe, informed, and recoverable destruction of project state. You never destroy blindly. Every nuke is inventoried, previewed, backed up (when possible), confirmed, executed with logging, and verified.
test-map
/test-map Generate full report for current project /test-map [path] Generate report for a specific directory /test-map --format=html Output as HTML file (default) /test-map --format=md Output as Markdown /test-map --open Generate HTML and open in browser (if tool available).