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 OutlineDriven/outline-driven-development --skill buzzword-analysisgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/buzzword-analysis)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/buzzword-analysis"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/buzzword-analysis.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00792 |
| Opus 5 | $0.00017 | $0.00396 |
| Sonnet 5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
buzzword-analysis 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buzzword analysis
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants a description of the current jargon weather without advocacy. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Web searches and public-source reads are the only outward operations. |
| Side effect | A jargon-weather report returned as chat output, taking no side. |
| Done | The current jargon field is described from verifiable external sources, each term has a weather state or an explicit unclear label, and the report takes no side. |
Inputs
- The domain or field whose jargon is to be surveyed (a technology, market, or community). If none is named, ask once and stop until it is supplied.
- Optional: a time window or a set of specific terms to include. If omitted, survey the present field.
- Optional: specific sources to consult (search engines, industry publications, community forums). If omitted, select public sources that show recent usage.
Procedure
- Identify the domain the user named. If none is named, ask once and stop; do not fabricate a domain. Done when: the domain is identified or the user is asked for one.
- Search verifiable external sources for terms currently circulating in that domain. Use web search, public forums, industry publications, and vendor documentation. Record which source each term was found in and the date of the evidence. A term claimed from model knowledge without a source is marked unverified. Done when: circulating terms are listed with their sources and evidence dates.
- For each term, separate its descriptive meaning from its rhetorical or marketing freight: what it denotes versus what adopting it signals. Done when: each term has its descriptive meaning separated from its signaling freight.
- Classify each term's weather state as rising, peak, fading, or residual, based on the usage trajectory the sources show. When the sources do not support a trajectory call, label the term unclear rather than guessing. Done when: each term has a weather state or an unclear label with the reason.
- Where a term's popular meaning has drifted from its technical origin, note the drift without correcting it. Done when: drift is noted where present.
- Present the field as a weather report: which terms are hot, cooling, or stale, and what each is being used to sell or signal. Done when: the field is presented as a weather report.
- Take no position on whether any term or its adoption is good or bad. Describe; do not advocate. Done when: the report takes no side on adoption.
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.
- yesterday Changed · -18 tokens per session 6f94e4eb9649
- 4d ago First seen · 45 lines · 52 tokens per session scan A ffe66aa79a94
buzzword-analysis is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 792 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.