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 tail-preserving-task-output-truncationgit 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/tail-preserving-task-output-truncation)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/tail-preserving-task-output-truncation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/tail-preserving-task-output-truncation/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/tail-preserving-task-output-truncation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/tail-preserving-task-output-truncation.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 | $0.00377 |
| Opus 5.5 | $0.00012 | $0.00151 |
| Sonnet 5.5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
tail-preserving-task-output-truncation 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: Tail-Preserving Task Output Truncation
Domain: task-output
Trigger: Use this when a task produces output larger than the session’s configured limit and you need to keep a concise preview plus a persistent archive.
Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Track each task’s output size before emitting it. If it exceeds the configured limit, store the full output on disk, prepend a header that points to the saved file, and emit only the final slice of the log that still fits. Keeping the tail preserves the most recent progress or failure details while the persisted artifact holds the complete transcript.
Key Rules
- Keep the configured output cap as the guardrail and only trim once per emission rather than chopping arbitrarily mid-stream.
- Write a clear header that points to the saved file so downstream readers can fetch the complete data on demand.
- After trimming, emit exactly available space characters from the end, not the start, so the most recent progress is preserved.
- Use a deterministic artifact path so every truncated preview points to a stable location.
Example Application
When a build step emits 100 KB of logs, save the full output to a file such as tool-results/build-task.txt, then return only the tail of the log plus a header that tells the reader where the full output lives.
Anti-Patterns (What NOT to do)
- Don’t trim from the beginning of the output where the useful part usually is.
- Don’t drop the header—the reader must know where to find the untrimmed record.
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 220bacc64a4b
tail-preserving-task-output-truncation 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 377 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
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.
static
Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.
merge
Resolve an in-progress merge or rebase by the intent of both sides, re-run the full gate on the merged tree, and finish the operation.
tilth
Use the tilth CLI for code reading, outlining, search, callers, blast-radius deps, and structural diffs. Activate when the user asks to explore a repo, find a symbol, trace callers, read a file, view a diff, or analyze impact. Prefer tilth over grep/cat/find/ls — one invocation returns AST-aware outlines, definitions…
fix
Resolve blocking review gaps through bounded repairs and independent re-review; diagnose stalled attempts without expanding scope.
cleanup
Find duplicates, dead links and untagged items in a saved library and propose what to do about each.