delete-reports

delete-reports is a skill for Claude Code from mappedsky/seizu. It costs 51 tokens per session (691 once invoked), scanned A, original, Apache-2.0.

A report deletion tool for removing one Seizu report and all of its saved versions. It confirms which report is intended before requesting approval for the permanent deletion.

In plain words
What is it for?
Use it to delete a report, draft, or review copy after checking what will be removed and requesting confirmation.
Why use it?
It prevents deleting the wrong report and makes clear that the report and its versions cannot be restored.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to delete a report, draft, or review copy after checking what will be removed and requesting confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mappedsky/seizu/delete-reports
Install

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.

Any agent
npx skills add mappedsky/seizu --skill delete-reports
Clone the repo
git clone --depth 1 https://github.com/mappedsky/seizu

Made for: Claude Code.

Wrote 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.

agentmods badge for delete-reports

README.md
[![agentmods](https://agentmods.dev/badge/skills/mappedsky/seizu/delete-reports/github.svg)](https://agentmods.dev/skills/mappedsky/seizu/delete-reports)
Your own site
<a href="https://agentmods.dev/skills/mappedsky/seizu/delete-reports"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/delete-reports/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.

agentmods 80×15 button for delete-reports

Your own site · 80×15
<a href="https://agentmods.dev/skills/mappedsky/seizu/delete-reports"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/delete-reports.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00691
Opus 5.5 $0.00020 $0.00276
Sonnet 5.5 $0.00010 $0.00138
Haiku 4.5 $0.00005 $0.00069

Measured 1mo ago against content hash c885f033ea69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

delete-reports 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.

.config/dev/seizu/plugins/report-authoring/skills/delete-reports/SKILL.md · 56 lines

What it actually says

Delete a Seizu report for the request the request input carries.

Inputs — the values arrive in the ## Inputs block below these instructions:

  • request — the deletion to make and why.
  • target_report_id — the report to delete, if known.
  • report_name — the report's name, when the id is not known.
  • dry_run — when true, produce the payload without deleting anything.

Tool arguments - use exactly these field names and no others:

  • reports__list: no arguments
  • reports__get: report_id
  • reports__list_versions: report_id
  • reports__delete: report_id

Deletion rules:

  • A delete removes the report and all of its versions, and cannot be undone. There is no restore, so identify the report before calling anything.
  • Delete exactly one report per request unless the user has named several. Never widen a request into a cleanup of everything that looks similar.
  • reports__delete is confirmation-gated: the call returns an approval request rather than deleting. Say so plainly and tell the user to approve it in the chat's confirmations panel. That is the expected path, not a failure, and not a reason to look for another way to remove the report.
  • A pinned report, or the one the dashboard points at, may refuse deletion. Report the refusal and what would have to change first; do not unpin or repoint the dashboard unless the user asks.

Workflow:

  1. If target_report_id is empty, call reports__list and identify the report from report_name and the request. If more than one matches, or none does, ask for the exact report and stop.
  2. Call reports__get and confirm the report's name, latest version and access scope. Say what is about to be destroyed, naming the report rather than only its id.
  3. Call reports__list_versions and state how many versions go with it.
  4. If dry_run=true, stop here and show the exact reports__delete payload.
  5. If dry_run=false, call reports__delete with report_id. Report the approval request if one comes back, and after it is approved confirm the deletion.
  6. Verify by calling reports__get for the same id; a deleted report is gone.

Output format:

  • Target: report_id, name, access scope, latest version, version count.
  • Impact: what the deletion destroys, and anything that blocks it.
  • Applied Changes: the reports__delete call and its result, or the dry-run payload, or the approval that is waiting.
  • Verification: evidence the report is gone.
Changes

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.

  1. 1mo ago First seen · 56 lines · 51 tokens per session scan A c885f033ea69

Subscribe to this mod's changes

delete-reports is a skill published in the GitHub repository mappedsky/seizu (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 51 tokens to every session and 691 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 2026-09-11.