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 api-round-ptl-retry-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/api-round-ptl-retry-truncation)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/api-round-ptl-retry-truncation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/api-round-ptl-retry-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/api-round-ptl-retry-truncation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/api-round-ptl-retry-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 | $0.00040 | $0.00461 |
| Opus 5 | $0.00020 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
api-round-ptl-retry-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 11d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: API-Round PTL Retry Truncation
Domain: compaction Trigger: Apply when the compaction request itself hits prompt-too-long and you need a last-resort retry path that removes old context without breaking API message validity. Source Pattern: Distilled from reviewed session memory, compaction, and context-budgeting implementations.
Core Method
Recover from a prompt-too-long summary attempt by trimming whole API-round groups from the head of the message list instead of slicing arbitrary messages. Size the drop by the reported token gap when available, or by a fallback fraction when it is not, and keep at least one summarizeable group. If trimming leaves the message list starting with an assistant turn, prepend a synthetic user marker so the next retry still satisfies the API's user-first contract.
Key Rules
- Group by assistant-response boundaries, not raw human turns, so each dropped unit preserves tool-use pairing semantics as much as possible.
- Strip any prior synthetic retry marker before regrouping so repeated retries keep making progress instead of dropping only the marker.
- Keep at least one group after truncation; return
nullwhen nothing safe remains to summarize. - Use the parsed token gap when available, but fall back to a deterministic percentage when the provider error format does not expose it.
- Repair assistant-first retries with a synthetic user preamble so the request remains API-valid after head truncation.
Example Application
If a compaction call on a long single-user-turn session still exceeds the limit, group the transcript by API rounds, drop the oldest rounds until the estimated gap is covered, and retry with a synthetic meta user line when the remaining transcript would otherwise start with an assistant block.
Anti-Patterns (What NOT to do)
- Do not trim arbitrary individual messages from the head; you can strand tool-use sequences and create invalid retry payloads.
- Do not keep reusing the previous retry marker as part of the grouped history or each retry can stall without reducing real context.
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.
- 11d ago First seen · 29 lines · 40 tokens per session scan A dc13a5d1697a
api-round-ptl-retry-truncation is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 461 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 2026-08-30.
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.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
ackit-context-optimization
Build budgeted context packs and trim instruction bloat for coding agents.
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
k-knowledge
Instructions for recording stable project facts in AGENTS.md or a project map. AGENTS.md is a file that stores guidance for coding agents.