api-round-ptl-retry-truncation

api-round-ptl-retry-truncation is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 40 tokens per session (461 once invoked), scanned A, original, MIT.

A recovery procedure for when a compaction request is too long for the API. It removes the oldest complete conversation groups and adds a temporary user marker when needed so the retry remains valid.

In plain words
What is it for?
Use it during prompt-too-long failures in compaction, especially when older conversation context must be dropped while preserving usable tool and assistant message structure.
Why use it?
It lets context summarization retry without cutting messages arbitrarily or producing an invalid message sequence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it during prompt-too-long failures in compaction, especially when older conversation context must be dropped while preserving usable tool and assistant message structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/api-round-ptl-retry-truncation
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 ychampion/cskill-agents --skill api-round-ptl-retry-truncation
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

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 api-round-ptl-retry-truncation

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/api-round-ptl-retry-truncation/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/api-round-ptl-retry-truncation)
Your own site
<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.

agentmods 80×15 button for api-round-ptl-retry-truncation

Your own site · 80×15
<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>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 461 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 $0.00040 $0.00461
Opus 5 $0.00020 $0.00230
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 11d ago against content hash dc13a5d1697a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

agents/claude-code/skills/api-round-ptl-retry-truncation/SKILL.md · 29 lines

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 null when 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.

Read the full file on GitHub · 29 lines

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. 11d ago First seen · 29 lines · 40 tokens per session scan A dc13a5d1697a

Subscribe to this mod's changes

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.