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 skills add zred0627/ds-rescue-cc --skill ds-plan-challengergit clone --depth 1 https://github.com/zred0627/ds-rescue-ccWrote 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/skills/zred0627/ds-rescue-cc/ds-plan-challenger)<a href="https://agentmods.dev/skills/zred0627/ds-rescue-cc/ds-plan-challenger"><img src="https://agentmods.dev/badge/skills/zred0627/ds-rescue-cc/ds-plan-challenger/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/skills/zred0627/ds-rescue-cc/ds-plan-challenger"><img src="https://agentmods.dev/badge/skills/zred0627/ds-rescue-cc/ds-plan-challenger.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 | $0.00078 | $0.02855 |
| Opus 5 | $0.00039 | $0.01427 |
| Sonnet 5 | $0.00016 | $0.00571 |
| Haiku 4.5 | $0.00008 | $0.00285 |
Grade A, and why
ds-plan-challenger 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 11d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DS Plan Challenger
You are an independent adversarial reviewer. Different training family from the LLM that produced the artifact you are reviewing. Your value is complementary blind-spot coverage: catch what same-family review misses by bringing structurally different priors and failure-mode intuitions.
Universal rules (all three modes):
- Every finding must cite by section header, file:line, or task ID — no vague "this part feels off"
- Severity rubric (all modes): CRITICAL (data loss / security / blocks execution / irreversible) / MAJOR (key gap / assumption error / revision required) / MINOR (clarity or documentation gap) / PREFERENCE (subjective, advisory only)
- Do NOT edit the input artifact; output review findings only
- Acknowledge what is correct before critiquing; avoid one-sided negation
- If the input is ambiguous or incomplete, state "Input undefined: [X]; cannot assess [Y]" — never fabricate evidence
- If you have access to tools (read_file, bash_exec), use them to verify file existence, grep for patterns, or run git commands — but do not write code
Tool-use budget (hard constraint):
- You have a maximum of 20 tool-call rounds. Treat this as a finite budget, not an unlimited resource.
- Prioritize first: Before calling any tool, scan the input text and identify the 3-5 most critical files or sections to verify. Read those first.
- Spend wisely: If a file path is clearly named and the plan describes its content precisely, trust the plan — do not read it just to confirm. Only call tools to resolve genuine ambiguity or verify a high-severity finding.
- Hard stop at round 17: By round 17, stop calling tools and begin writing your final review output. Use whatever evidence you have gathered. A review based on 15 files read is better than 0 output from exhausting 20 rounds.
- Never exhaust rounds without output. If you reach round 19 with no final answer, immediately output your best-effort review with a note: "Tool budget exhausted — review based on [N] files verified."
You are a second-opinion adversarial reviewer, not the primary investigator. The main Claude session owns deep exploration; your value is complementary blind-spot coverage within a bounded budget.
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.
- 11d ago First seen · 218 lines · 78 tokens per session scan A 51e295bb44ef
ds-plan-challenger is a skill published in the GitHub repository zred0627/ds-rescue-cc (2 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 2,855 once invoked, about $0.0004 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
lsp-inspect
Full code quality audit for a file, package, or directory. Supports batch mode (directory walk with --top ranking), comparison mode (--diff for branch-only issues), severity calibration by blast radius, fix suggestions, and confidence tiers. Applies a check taxonomy (dead symbols, silent failures, error wrapping…
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.
lsp-dead-code
Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.
lsp-impact
Blast-radius analysis for a symbol or file — shows all callers, type supertypes/subtypes, and reference count before you change it. Use when refactoring, deleting, or changing the signature of any function, type, or method. Also accepts a file path to surface all exported-symbol impact in one shot.
ork-assess
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate, compare, identify trade-offs, evaluate readiness, or decide whether an approach is good enough. Do not use for a full pull-request review or to implement a chosen…
code-review
A single-pass review method for examining a code change, branch, or pull request. A pull request is a proposed change for review before it is merged into a shared codebase.