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-prgit 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-pr)<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-plan-pr"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-plan-pr/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-pr"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-plan-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00056 | $0.01182 |
| Opus 5.5 | $0.00022 | $0.00473 |
| Sonnet 5.5 | $0.00011 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
speq-plan-pr 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Planner, PR flow (Orchestrator)
This skill runs /speq-plan and ships the result as a draft PR. It writes no plan content itself. planner-agent and plan-reviewer do that, through /speq-plan.
Required Skills (for the orchestrator)
Invoke before starting:
/speq-cli: spec discovery/speq-writing-guardrails: prose style for artifacts and GitHub text/speq-git-operations: the git/gh operation-to-command mapping, safety rules, and return formats.
Workflow
0. Load Project Hook
Check for .speq/plan-pr-hook.md in the repo root.
- Present: read it. Announce "Loaded project hook: .speq/plan-pr-hook.md". Its content is authoritative: it can add to, change, or override any part of this workflow. If the hook conflicts with this workflow, the hook wins.
- Absent: continue without mention.
1. Resolve Target
If the argument is a plan name, PR number, or branch, check it out:
Run — operation: checkout (per /speq-git-operations)
target: <the raw argument>
- Found, with a PR: go to step 3 (revise).
- Not found, or the argument is feature intent text: go to step 2 (new plan).
2. New Plan
- Run
/speq-plansteps 0 to 6: discovery, the clarifying interview, the plan name,planner-agent, and the one review with its fix pass. Skip its step 7. - Create the branch. The plan files are uncommitted, so they carry over:
Run — operation: create-branch (per /speq-git-operations) branch: feat/<plan-name> - Ship the draft, per Ship.
3. Revise from PR Comments
Run this when step 1 found a PR for the target.
- Read the feedback:
Run — operation: read-comments (per /speq-git-operations) since: <timestamp of the last `spec(plan)` commit on this branch> - Treat every returned comment as user feedback on the files the PR changed: the PR conversation, review summaries, and inline comments on any file. Write them to
specs/_plans/<plan-name>/notes/pr-feedback.md, one entry per comment with its file and line when it has them.notes/is never committed. - If no comment is new, report that and stop.
- Respawn
planner-agentwith the path tonotes/pr-feedback.md, per/speq-planning's Revision Mode. If a comment is ambiguous, ask the user. - Run
/speq-planstep 6 on the revised plan. - Commit and push, and answer on the PR:
Run — operation: commit (per /speq-git-operations) paths: the plan directory, excluding specs/_plans/<plan-name>/notes/ message: spec(plan): address PR feedback for <plan-name> Run — operation: push (per /speq-git-operations) Run — operation: comment-pr (per /speq-git-operations) comment_body: one line per comment, `Resolved` or `Could not resolve` with the reason
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.
- yesterday Changed · -167 lines · -35 tokens per session 763007493cd5
- 12d ago Changed · +1 lines cf3309730783
- 19d ago Changed · -2 lines ded36e6ddbdf
- 22d ago Changed · +6 lines fa6a12b3daa7
- 1mo ago Changed · +5 lines f0184a232f7b
- 1mo ago Changed · +3 lines 617d33fa412c
- 1mo ago First seen · 251 lines · 91 tokens per session scan A 34e0767d0c40
speq-plan-pr is a skill published in the GitHub repository marconae/speq-skill (55 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,182 once invoked, about $0.0002 per session on Opus 5.5. 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
codex-issue-coordinator
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.
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.
task-to-pr
Delivers specs or decided tasks as tested, independently reviewed pull requests. Runs the CI and review repair loop, then leaves passing pull requests open unless merging was explicitly authorized.
factory
Delivers a spec or decided task through the task-to-pr workflow and merges after all quality and approval gates pass. Explicit invocation grants merge authority for the supplied work.
ase-repo-review
Perform a holistic, human-reviewer-style critique of the currently staged Git changes (or, with --unstaged, of the unstaged and untracked changes, with --branch, of a branch against its base, or, with --commit, of a single commit) and emit an approve/reject verdict with prioritized, severity-tagged, line-cited…
ase-repo-dissect
Dissect the current Git change set, treated as an epic, domain-wise and logically into cohesive parts and materialize each part in its own dedicated Git WorkTree. Use when the user calls to "dissect", "split", "break up", or "decompose" a large change set into atomic, separately committable parts.