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 marconae/speq-skill --skill speq-plan-reviewgit clone --depth 1 https://github.com/marconae/speq-skillWrote 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/marconae/speq-skill/speq-plan-review)<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-plan-review"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-plan-review/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/marconae/speq-skill/speq-plan-review"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01631 |
| Opus 5 | $0.00020 | $0.00816 |
| Sonnet 5 | $0.00008 | $0.00326 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
speq-plan-review 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Plan Review
Build the case against approval, not for it.
Method
Premortem first. Before scoring anything, write: "six months from now this plan failed catastrophically — why?" Produce 2-3 concrete failure stories. Route each into the taxonomy below. A failure story with no matching category means the taxonomy misses a category, not that the story does not count.
No silent pass. For every axis below, either raise a finding or write one line certifying "no objection — axis checked" with the evidence checked. Never skip an axis.
Round 2 (if applicable): first re-check every round-1 BLOCKER against the revised artifacts and the [plan-review] entries in decision-log.md. Confirm each is resolved, not reworded, listing each as Resolved: or Not resolved: per the output template.
Plan Size: full(the orchestrator's default when it omits the field): then do a fresh pass for new findings, across all six axes, same as round 1.Plan Size: small: skip the fresh pass. The findings document holds only## Summaryand## Round-1 Blocker Recheck— no axis sections. The orchestrator classifies the plan assmallfrom artifacts already on disk (fix-verb plan name, no## Designsection inplan.md, empty## Design Decisionsindecision-log.md) and passes it as an explicitPlan Size:field in the round-2 respawn prompt.
Non-goal: do not re-litigate decisions the user made in the clarifying interview. Challenge how the plan operationalizes those decisions, not the decisions themselves. If the user said "use approach X" and the plan uses X, check whether X is executed soundly, not whether X was the right call. A deviation the brief notes as authorized by an active project hook is settled the same way; do not raise it as a finding.
Challenge Taxonomy
Tag every finding. Group findings by axis in the output.
Intent fidelity: does the plan match what the user asked for?
[INTENT_DRIFT]: the plan reinterprets or substitutes a different problem than the one asked. Quote the original request; quote the plan line that diverges.[SCOPE_CREEP]: work with no traceable user need: gold-plating, speculative flexibility, "while we're here" extras.[SCOPE_REDUCTION]: part of the ask dropped, deferred, or reframed as out-of-scope without user agreement.
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.
- 3d ago Changed · +12 lines b32db8911dd4
- 10d ago First seen · 80 lines · 40 tokens per session scan A e1d6703d3142
speq-plan-review is a skill published in the GitHub repository marconae/speq-skill (50 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 1,631 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
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
release-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.
need-explorer
Clarify intent, scope, constraints, and success criteria before artifact creation. Invoke when the request is fuzzy, the user is comparing options, or the workflow needs a stable change definition before writing artifacts.