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 LandonSchropp/agent-toolkit --skill self-destructgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/self-destruct)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/self-destruct"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/self-destruct/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/landonschropp/agent-toolkit/self-destruct"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/self-destruct.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 | $0.00052 | $0.00621 |
| Opus 5.5 | $0.00021 | $0.00248 |
| Sonnet 5.5 | $0.00010 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
self-destruct 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Destruct
Time-boxed work leaves debris behind. A self-destruct records what to delete, when, and why, where an agent will actually read it.
REQUIRED: Invoke the ls-code:project-conventions skill for AGENTS.local.md and CLAUDE.local.md.
Mark The File
Markdown gets a callout, at the top of the file after any frontmatter:
> [!warning] Self-Destruct
> Delete this note after 2026-09-05, once the interview loop is over. It documents a single time-boxed project, and nothing in it generalizes.
Outside a vault, where that callout renders as a literal blockquote, use > **Self-Destruct:** and the same two sentences.
Anything with comment syntax gets one comment line, after any shebang:
# Self-Destruct: delete this file after 2026-09-05, once the migration has landed.
A format with no comments — JSON, CSV, an image — gets no marker, which makes the entry below its only record. A directory gets its marker in the README, or none if it hasn't got one.
Always an absolute date. "In three weeks" is unreadable by the time it matters.
Record It in AGENTS.local.md
The marker only fires if someone opens the file, so the instruction also goes where every session reads it. Add an entry under a ## Self-Destructs section in the repository's AGENTS.local.md:
## Self-Destructs
- After 2026-09-05, delete `<path>` and `<path>`, remove their lines from `.git/info/exclude`, and delete this entry. <Why this existed and why it stops mattering then.>
The deleting agent never loads this skill, so the entry has to stand alone: every path, its exclude lines, and the entry itself.
Keep It Out Of Version Control
A self-destructing file isn't committed unless the user asks for it. Add its path to .git/info/exclude, which is local to the clone and never committed itself. Not .gitignore — that is committed, so it would outlive the file it excludes.
Destroying
This skill sets the trap; it doesn't spring it. There is no sweep to run and nothing to check on a schedule. When you read an entry whose date has passed, delete what it names — the entry included — as part of whatever you were already doing, then tell the user what went. The ## Self-Destructs section goes with the last entry under it.
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.
- 1mo ago Changed · +1 lines · +4 tokens per session c3812aaf46f3
- 1mo ago First seen · 51 lines · 48 tokens per session scan A 4e86c7895603
self-destruct is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 621 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
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
press-clip
Turn a live article URL into a press clip that looks like the real coverage — the publication's own logo, fonts, photos and layout kept intact, the ads and clutter removed, and (for a roundup) just the client's section. Renders to PDF. You inspect each site and tailor the removal; the bundled script carries no…