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 ychampion/cskill-agents --skill idempotent-tool-result-persistencegit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/idempotent-tool-result-persistence)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/idempotent-tool-result-persistence"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/idempotent-tool-result-persistence/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/ychampion/cskill-agents/idempotent-tool-result-persistence"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/idempotent-tool-result-persistence.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 | $0.00030 | $0.00420 |
| Opus 5.5 | $0.00012 | $0.00168 |
| Sonnet 5.5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
idempotent-tool-result-persistence 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.
What it actually says
SKILL: Idempotent Tool Result Persistence
Domain: persistence
Trigger: Use this when tool result blocks exceed their configured thresholds and you want to persist them once while still returning a preview.
Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Persist oversized tool outputs to a deterministic artifact path derived from the tool call ID and content type. Create that artifact with exclusive-write semantics so retries and concurrent writers cannot clobber or duplicate the same payload. After the first successful write, return a compact preview plus metadata pointing at the persisted artifact; later retries should reuse the existing file and regenerate the same preview without rewriting the payload. This keeps large outputs accessible while making persistence safe and repeatable.
Key Rules
- Create the parent directory once per storage root, but write each artifact with exclusive creation semantics.
- If the target artifact already exists, treat that as a successful prior write and move directly to preview generation.
- Keep preview metadata explicit: content type, truncation status, persisted path, and original size should all be recoverable downstream.
- Log the persisted location and size so operators can trace where a large result went.
Example Application
When a log-reading tool returns 60 KB of text, write it once to a stable artifact file such as tool-results/<tool-call-id>.txt, then send only a short preview plus the saved path. If the same result is replayed on retry, skip the write and reuse the same artifact reference.
Anti-Patterns (What NOT to do)
- Don’t re-write the same file on retries; failing to check
EEXISTcauses EOS errors and clobbers the previous log. - Don’t drop the preview header; consumers depend on
<persisted-output>tags to know the persisted location.
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 First seen · 28 lines · 30 tokens per session scan A ded22ded75f8
idempotent-tool-result-persistence is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 420 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.