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 tool-success-aware-memory-suppressiongit 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/tool-success-aware-memory-suppression)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/tool-success-aware-memory-suppression"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/tool-success-aware-memory-suppression/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/tool-success-aware-memory-suppression"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/tool-success-aware-memory-suppression.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 | $0.00390 |
| Opus 5 | $0.00015 | $0.00195 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
tool-success-aware-memory-suppression 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 8d 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: Tool Success Aware Memory Suppression
Domain: memory-selection Trigger: Apply when contextual docs or memories should stay hidden for tools that are already working, but remain available for tools that failed or have unknown outcomes. Source Pattern: Distilled from reviewed turn-local memory selection and tool-outcome suppression implementations.
Core Method
Scan the current human-turn window, pair tool invocations with their results, and suppress context only for tools that show clear success with no failures in that window. If any call failed or no result arrived yet, keep that tool eligible for docs or memories so the runtime spends budget on unresolved problems instead of re-explaining tools that are already working. This keeps context targeted at the model's current points of friction.
Key Rules
- Bound the scan to the current human-turn window so old successes do not suppress guidance for a new problem.
- Match invocations to results through stable IDs before resolving suppression by tool name.
- Treat any failure as a reason to keep that tool's docs available, even if other calls succeeded.
- Do not suppress tools with missing results; unresolved work should remain eligible for help.
Example Application
If the model successfully uses file-reading tools several times while still struggling with shell execution, suppress context docs for the file-reading tools during this turn and keep shell guidance eligible because the failures show it still needs help there.
Anti-Patterns (What NOT to do)
- Do not suppress docs just because a tool was invoked; invocation without a result says nothing about whether the tool is understood.
- Do not let one earlier success hide docs after a later failure for the same tool; the failure reopens the need for guidance.
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.
- 8d ago First seen · 28 lines · 30 tokens per session scan A 15f6f4254dff
tool-success-aware-memory-suppression is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 390 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 2026-09-03.
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.
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.