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 SebaBoler/vanguard --skill tech-specgit clone --depth 1 https://github.com/SebaBoler/vanguardWrote 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/sebaboler/vanguard/tech-spec)<a href="https://agentmods.dev/skills/sebaboler/vanguard/tech-spec"><img src="https://agentmods.dev/badge/skills/sebaboler/vanguard/tech-spec/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/sebaboler/vanguard/tech-spec"><img src="https://agentmods.dev/badge/skills/sebaboler/vanguard/tech-spec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.00537 |
| Opus 5.5 | $0.00020 | $0.00215 |
| Sonnet 5.5 | $0.00010 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00054 |
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 12d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Spec
Research the codebase read-only and produce a precise technical specification for the given task. Do not edit, create, or delete any source files.
Sections to include
Problem
What exactly needs to be solved and why. Identify the gap between the current state and the desired state. Name the stakeholders and the concrete pain point. Check the ticket's premise against the code first: if the proposed mechanism already exists, or the real gap is elsewhere, say so here and re-scope the spec to the actual gap rather than specifying a duplicate.
Architecture
Components involved, interfaces changed or added, data flows, and integration points with the rest of the system. Include sequence or data-flow sketches if the interaction is non-trivial.
Acceptance Criteria
Numbered, testable conditions that define done. Each criterion must be verifiable without ambiguity
from the repository state and the diff alone: a command that exits 0, a test that passes, a file
that contains or no longer contains something. Never require an artifact outside the repo (a file
under /tmp, a captured baseline), a CI run, or a particular commit message — the autonomous
implementer controls none of those (the factory writes the commit message itself from the task
title), and such a criterion only turns a complete change into a "partial scope" delivery. Put any baseline
numbers the implementer must match into the spec itself. The one PR-body criterion that is allowed is
the one CLAUDE.md prescribes: when the task needs a CI-config edit the agent must not make, the AC
is "the PR body describes the needed edit for a human to apply".
Tests
Test cases and scenarios that must pass, including edge cases, failure paths, and integration boundaries. Name the test file(s) and key scenarios explicitly.
Risks
Known unknowns, edge cases, backward-compatibility concerns, and failure modes. Call out any assumption that, if wrong, would invalidate the design.
Performance / Scalability
Throughput and latency expectations, growth projections, and any bottleneck or scaling limit introduced or removed by the change.
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.
- 12d ago Changed · +10 lines e7c43961aa24
- 1mo ago First seen · 39 lines · 51 tokens per session scan A b62327e942ba
tech-spec is a skill published in the GitHub repository SebaBoler/vanguard (4 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 537 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 2026-08-31.
Other skills, from other repositories
node-modules-inspector
Inspects a project's installed nodemodules and produces three reports: duplicated packages (installed in multiple versions), packages sorted by install size, and maintenance actions (dep-upgrade opportunities + publint findings, grouped by consumer/author). Use when the user wants to audit dependencies, find duplicate…
setup-wizard
Interactive conversational setup wizard for instar. Walks users through initial configuration and identity bootstrapping conversationally.
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
spec-converge
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available…
phaser-pixi-2d-games
Use when building a 2D web game with Phaser (3.x/4.x) or PixiJS 8 in TypeScript - framework vs renderer, Phaser scenes/game objects/arcade physics/groups as pools/scale manager/loader, scene shutdown cleanup, PixiJS 8 async init, Assets bundles, ticker units and destroy, and keeping rules in plain TS modules.
instar-dev
Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). Wraps /build with mandatory side-effects review, signal-vs-authority principle check, and artifact generation. Structural enforcement via pre-commit/pre-push hooks — the instar repo refuses…