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/superplan-md/superplan-plugin/superplan-debugnpx skills add superplan-md/superplan-plugin --skill superplan-debuggit clone --depth 1 https://github.com/superplan-md/superplan-pluginWhat 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 | $0.00032 | $0.00406 |
| Opus 5 | $0.00016 | $0.00203 |
| Sonnet 5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
superplan-debug 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.
What it actually says
Systematic Debugging
Overview
Debug by evidence and hypothesis, not patch roulette.
Root-Cause Law
Do not start broad fixes before reproducing or characterizing the failure well enough to distinguish symptom from cause.
If the current evidence does not isolate the failure mode, gather more evidence first.
Hard Gate
Do not propose or apply speculative fixes before Phase 1 has produced a concrete failure model.
Trigger
Use when:
- execution is blocked by a bug, failing check, flaky result, or broken behavior
- unexpected behavior appears during tracked work
- the system is tempted to fix before understanding
Phases
- Reproduce or characterize the failure.
- Narrow the failure surface with logs, scripts, tests, and diagnostics already trusted by the repo.
- Form explicit hypotheses.
- Run the cheapest discriminating check.
- Fix the root cause.
- Verify against the relevant task contract and acceptance criteria.
Core Rules
- gather evidence from the repo's existing logs, scripts, harnesses, and diagnostics first
- change one variable at a time when narrowing the cause
- fix the root cause, not the most recent symptom
- if the bug reveals a durable trap, record it in
.superplan/gotchas.md - if the fix changes the intended path materially, update
.superplan/decisions.md
Forbidden Behavior
- guessing the fix before understanding the failure
- changing multiple variables at once and calling the result evidence
- treating one passing rerun as proof the root cause is solved
- rewriting the task contract just to make the bug look smaller
Handoff
Once root cause is clear, execution may continue through superplan-execute.
If the investigation reveals structural drift, hand back to superplan-shape.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 58 lines · 32 tokens per session scan A 3560b0c77b71
superplan-debug is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 406 once invoked, about $0.0002 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
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…