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/sd0xdev/sd0x-harness/tech-specnpx skills add sd0xdev/sd0x-harness --skill tech-specgit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/tech-spec)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/tech-spec"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/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 | $0.00054 | $0.01941 |
| Opus 5 | $0.00027 | $0.00971 |
| Sonnet 5 | $0.00011 | $0.00388 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
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 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Spec Skill
Trigger
- Keywords: tech spec, technical specification, spec review, review spec, feature design
When NOT to Use
- Creating request documents (use /create-request)
- Code implementation (use feature-dev)
- Architecture consulting (use /codex-architect)
Commands
| Command | Purpose | When |
|---|---|---|
/tech-spec |
Create or update tech spec | Auto-detects create/update from filesystem state |
/deep-analyze |
Deepen spec + roadmap | After initial concept |
/review-spec |
Review tech spec | Spec confirmation |
Context-Aware Mode (Upsert)
When invoked without a full requirement description, the skill auto-detects the target feature using
the cascade in references/native-feature-resolution.md — this skill's own reference, and
deliberately command-free.
This skill grants Bash(git:*) and not Bash(node:*), so the resolver script is not a command it
may run — and it does not link the shared reference that teaches it, because a file of unrunnable
commands inside this skill's reachable graph is the defect, not the annotation on it. The cascade
needs nothing beyond $ARGUMENTS, git branch --show-current, git diff --name-only HEAD and a
Glob over docs/features/*. What that does not produce is the four document source sets or
scan_error — this skill consumes neither. A skill that needs the sets (/architecture,
/tech-brief, /runbook, /ask) grants Bash(node:*) and reads the shared reference itself.
Canonical discovery is still owed, and testing one literal path does not deliver it. The spec
may have been split into a folder or may carry a variant name, and docs/features/auto-loop-evolution/2-tech-spec/2-tech-spec.md
in this repo is the live proof. Resolve it with a Glob over docs/features/<key>/, in this
order — the first hit wins:
| # | Glob | Meaning |
|---|---|---|
| 1 | docs/features/<key>/2-tech-spec.md |
Unsplit canonical spec |
| 2 | docs/features/<key>/2-tech-spec/2-tech-spec.md |
Split spec — the folder keeps the lifecycle prefix, the main file keeps the canonical filename (@rules/docs-numbering.md § Size Limit) |
| 3 | docs/features/<key>/2-tech-spec*.md, minus any hit matching -fp-brief.md or -tech-brief.md |
A variant (2-tech-spec-v2.md). The two suffixes are excluded because they are not specs: scripts/config/doc-taxonomy.json carries the same exclude_pattern for the same reason, and docs/features/seek-verdict/ holds a live 2-tech-spec-fp-brief.md that this glob would otherwise return as the canonical spec. Two or more remaining hits is ambiguity, not a match — report and take the Need Human exit rather than picking one |
What ships with it
2 files 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 First seen · 165 lines · 54 tokens per session scan A 0f70763b3382
tech-spec is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,941 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
cc10x-router
THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect…
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
plan-review-gate
Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.