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-hijackgit 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-hijack)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/buzzword-hijack"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/buzzword-hijack.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 | $0.00040 | $0.00795 |
| Opus 5 | $0.00020 | $0.00398 |
| Sonnet 5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
buzzword-hijack 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buzzword hijack
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to choose and execute a bounded positioning move that rides a jargon wave without confusing trend with truth. |
| Authority | Reversible local: writes only the named local positioning artifact (copy, landing, or messaging); rollback is undo (delete or revert the written artifact). No remote mutation. |
| Side effect | A bounded positioning move/artifact is written to a local file. No publish, deploy, or remote mutation. |
| Done | A bounded positioning move is executed and the artifact is written without confusing trend with truth. |
Inputs
- The product, project, or message to position. Required.
- The target surface for the positioning move: copy, landing page, or messaging. Required; state it before writing.
- The jargon wave to ride: the trending term or terms the user wants to use. Required; name the specific term(s).
- The output file path. Required.
Procedure
- Name the jargon wave: identify the specific trending term(s) the user wants to ride and the space they belong to. Done when: the jargon wave and its space are named.
- Separate trend from truth: list every factual claim about the product. Mark each claim that holds independently of the jargon. Any claim that only holds because of the jargon is a truth-substitution and must be removed or re-grounded. Done when: every factual claim is marked as holding independently or flagged as truth-substitution.
- Choose the bounded positioning move: pick which surface (copy, landing, or messaging) the jargon enters and where it stops. State the boundary explicitly: the jargon appears in positioning language, not in factual assertions. Done when: the surface and boundary are chosen and stated.
- Draft the positioning artifact: write the chosen surface so the jargon appears in the framing, headline, or hook while every factual claim stands on its own without the jargon. Done when: the artifact is drafted with jargon in framing and facts standing independently.
- Verify the trend-truth separation: re-read the artifact and confirm that no factual claim depends on the jargon. If a claim would be false or empty without the jargon, rewrite or remove it. Done when: no factual claim depends on the jargon.
- Write the artifact to the named local file. Report the file path, the chosen surface, the jargon term(s) used, and the boundary where the jargon stops. Done when: the artifact is written and the report is delivered.
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.
- 2d ago Changed · -9 tokens per session 4388e6d2d0b1
- 4d ago First seen · 42 lines · 49 tokens per session scan A 6e252ad162d2
buzzword-hijack is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 795 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.