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 dremonkey/agents-and-skills --skill plan-tech-specgit clone --depth 1 https://github.com/dremonkey/agents-and-skillsWrote 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/dremonkey/agents-and-skills/plan-tech-spec)<a href="https://agentmods.dev/skills/dremonkey/agents-and-skills/plan-tech-spec"><img src="https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/plan-tech-spec.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 5.1 | $0.00043 | $0.01906 |
| Opus 5 | $0.00022 | $0.00953 |
| Sonnet 5 | $0.00009 | $0.00381 |
| Haiku 4.5 | $0.00004 | $0.00191 |
Grade A, and why
plan-tech-spec 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 7d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTO Technical Plan Review Mode
Purpose
Use this skill when the plan is already defined at the product level and needs rigorous technical review before implementation.
Artifact Contract
This skill's primary artifacts are:
- Architecture documentation — update existing docs or create new ones, depending on scope (see Architecture Doc Policy below).
- EPIC document(s) stored in
tasks/<EPIC_NAME>that define implementation slices, sequencing, and constraints at an execution-planning level.
These artifacts are inputs to plan-eng-tasks.
Architecture Doc Policy
Architecture docs in docs/architecture/ are a living set of documents that explain how the system is built. They are organized by system or topic, not by initiative or epic.
Before creating architecture artifacts, read the existing docs in docs/architecture/ and assess whether the change should be integrated into an existing document or warrants a new one:
- Update existing docs when the change extends an existing system (e.g., a new pipeline node, a new adapter, a new handler). Find the doc that describes that system and add the new component to its diagrams, flow descriptions, and component list.
- Create a new doc at
docs/architecture/<SYSTEM_OR_TOPIC>.mdonly when the change introduces a genuinely new subsystem, a new cross-cutting concern, or a new architectural boundary that doesn't fit naturally into any existing doc. Name it after the system or topic it describes, not the initiative that created it.
Rule of thumb: if the feature is described in terms of an existing system ("add X to the Y pipeline"), it belongs in Y's architecture doc, not its own.
AskUserQuestion Format
Explain the issue in plain language in the question text. List the recommended option first with "(Recommended)" appended to its label, and put the reasoning and tradeoffs in the option descriptions. Batch related decisions as separate questions within one call (up to 4 per call).
Review Modes
Choose one mode and stick to it:
- SCOPE EXPANSION - grow technical ambition where leverage is high.
- HOLD SCOPE - keep scope fixed and maximize implementation rigor.
- SCOPE REDUCTION - minimize moving parts and ship smallest robust slice.
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.
- 7d ago First seen · 200 lines · 43 tokens per session scan A 5a78147b6374
plan-tech-spec is a skill published in the GitHub repository dremonkey/agents-and-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 1,906 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…