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 Tx1207/hello-scholar --skill manage-specsgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/manage-specs)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/manage-specs"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/manage-specs/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/tx1207/hello-scholar/manage-specs"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/manage-specs.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 | $0.00041 | $0.01080 |
| Opus 5.5 | $0.00016 | $0.00432 |
| Sonnet 5.5 | $0.00008 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
manage-specs 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Specs
Preserve a design that lets another reader understand what should change, why the choice follows from the evidence, and how to judge the result. A list of intended actions is not enough; make the relationships between goals, decisions, constraints, and consequences explicit.
Save a reviewable proposal as a draft once its purpose and concrete approach are clear, including material open questions; do not wait for every choice to be settled.
Choose the owner
Start from known design paths, then Indexes or targeted searches. Read the plausible owner in full with the relevant Architecture, code, tests, and evidence. Preserve an established project document owner instead of creating a competing Spec. For hello-scholar Specs:
- Revise when one Spec already owns the same capability and lifecycle.
- Create when the capability has an independent value, acceptance boundary, and lifecycle.
- Replace when the target design will supersede an adopted contract or implementation model.
Choose by the decision's responsibility and lifetime, not the number of changed files. Ask one focused question only when equally plausible owners would materially change the design.
A new Spec takes the next global number (counting rejected and superseded IDs, at least three digits), reuses the established Topic or the narrow capability boundary shown by Architecture and callers, and is named after the stable public capability rather than the chosen implementation approach: hello-scholar/specs/<topic>/SPEC-NNN-<name>/spec.md, for example batch-retrieval/SPEC-004-public-batch-retrieval-api.
Explain the design as a connected argument
Lead with the current recommendation or accepted decision, the objects and behavior that change, and the decisive reason. Connect the problem to a concrete design: who owns each decision and state, how data and control move, what callers observe, and what failures mean. Include the necessary implementation sequence with the check for each meaningful step. Explain a material alternative through the tradeoff that ruled it out.
What ships with it
4 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.
- 4d ago Changed ff827c60738b
- 9d ago Changed · +15 lines · +10 tokens per session 5ef69623e2e4
- 1mo ago Changed · -47 lines · -7 tokens per session e3bc89ebdcbf
- 2mo ago First seen · 88 lines · 38 tokens per session scan A 27a732822c4c
manage-specs is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 1,080 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.