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/matrixfounder/agentic-development/skill-spec-validatornpx skills add MatrixFounder/Agentic-development --skill skill-spec-validatorgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWhat 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 | $0.00023 | $0.02054 |
| Opus 5 | $0.00012 | $0.01027 |
| Sonnet 5 | $0.00005 | $0.00411 |
| Haiku 4.5 | $0.00002 | $0.00205 |
Grade A, and why
skill-spec-validator 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 2d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Spec Validator
[!IMPORTANT] TIER 2 (High Integrity): This skill acts as a mechanical gatekeeper for the
/vdd-enhancedworkflow.
1. Purpose
To strictly enforce "Requirements Hardening" by mechanically verifying that:
TASK.mdcontains a Requirements Traceability Matrix (RTM).PLAN.mdexplicitly covers every item in the RTM using Atomic Checklists.
2. Usage
Mode A: TASK Validation
Trigger: After Analysis Phase. Command:
python3 scripts/validate.py --mode task /absolute/path/to/docs/TASK.md
Checks:
- Presence of an RTM heading (h2–h4), matched flexibly:
## Requirements Traceability [Matrix],## N. ... (RTM), and the bare### N. Requirements (RTM)form are all accepted. - Columns
ID,Requirement.
Mode B: PLAN Validation
Trigger: After Planning Phase. Command:
python3 scripts/validate.py --mode plan /absolute/path/to/docs/PLAN.md /absolute/path/to/docs/TASK.md
Checks:
- Every RTM
IDin TASK appears as a whole token somewhere in PLAN — in a step heading (## Step 1 — ... (R1)) or a- [ ] R1 ...bullet.R1does not satisfyR10.
3. Failure Handling
- Exit Code 1: Issues found. Orchestrator should trigger a Correction Loop (instruct Analyst/Planner to fix).
- Bypass: If validation is buggy, add the bypass token —
BYPASS_VALIDATIONin square brackets — toTASK.md.[!WARNING] The bypass is a bare substring test anywhere in
TASK.md, so a spec that merely mentions the token switches its own gate off and printsValidation bypassed …with exit 0 — which reads like a pass. Write it only when you mean it (that is why this section spells the token out instead of quoting it). Pinned by a test, deliberately not "fixed": tightening it is a behavior change to a live gate.
4. Dependencies
- Python 3 (stdlib only)
validate.py(inscripts/)
Execution Mode
- Mode: script-first. The whole judgement is mechanical — two regex matchers and a table parser. Nothing here is prompt-side; if a matcher disagrees with an artifact, that is a finding for a human, not something to reason around.
What ships with it
9 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.
- scripts/.keep 0 B
- scripts/tests/_fixtures.py 3.1 KB runs code
- scripts/tests/run_tests.sh 1.8 KB runs code
- scripts/tests/test_anchor.py 9.1 KB runs code
- scripts/tests/test_corpus.py 11 KB runs code
- scripts/tests/test_multitable.py 8.8 KB runs code
- scripts/tests/test_validate.py 13 KB runs code
- scripts/tools/compat_diff.py 3.0 KB runs code
- scripts/validate.py 17 KB runs code
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.
- 2d ago First seen · 127 lines · 23 tokens per session scan A dd492f30cc9e
skill-spec-validator is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 23 tokens to every session and 2,054 once invoked, about $0.0001 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
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文,通过迭代优化内容,并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…