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 dongshuyan/compass-skills --skill run-history-skill-upgradergit clone --depth 1 https://github.com/dongshuyan/compass-skillsWrote 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/dongshuyan/compass-skills/run-history-skill-upgrader)<a href="https://agentmods.dev/skills/dongshuyan/compass-skills/run-history-skill-upgrader"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/run-history-skill-upgrader/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/dongshuyan/compass-skills/run-history-skill-upgrader"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/run-history-skill-upgrader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 51 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00091 | $0.01407 |
| Opus 5 | $0.00046 | $0.00704 |
| Sonnet 5 | $0.00018 | $0.00281 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
run-history-skill-upgrader 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 13d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run History Skill Upgrader
Language Policy
Write all user-facing output in the user's language. Default to Chinese when the language is unknown.
Role
Turn real run feedback into structural net improvement for an existing skill. Upgrades may add, modify, merge, delete, deprecate, or decide not to change anything.
Portability
This skill is agent-agnostic. It should work in Codex, Claude Code, OpenCode, OpenClaw, Hermes, and similar local agent hosts that can read SKILL.md plus optional references/, scripts/, evals/, and agents/.
- Resolve
<skill-dir>from the directory that contains thisSKILL.md. - Let
<python>mean the host's available Python launcher:python3,python, orpy -3. - Do not assume a fixed skill root, shell, home-directory layout, or path separator.
- Placeholder paths such as
<skill-dir>/scripts/...describe path segments, not a required separator style. On Windows, use the separator style that your shell or harness accepts. - Treat platform-specific helper tooling as optional. Use it only when it is actually available.
Mandatory Two-Stage Approval
This skill always starts in plan_only.
plan_only: read the target skill and the agreed evidence scope, then produce a concrete upgrade plan and stop.apply_after_approval: modify files only after the user explicitly approves that specific plan.
The following are not approval by themselves:
- "upgrade it";
- "directly edit it";
- "don't ask me";
- "go ahead";
- the original request to improve a skill.
Valid approval must clearly point to the current plan, for example "approve plan A", "apply the plan above", or "yes, execute that upgrade plan".
Workflow
- Lock the target skill name and path.
- Lock
plan_onlyunless explicit post-plan approval already exists in the current conversation. - Lock the evidence scope: conversation, logs, screenshots, artifacts, diffs, tests, source docs, or user feedback.
- Read the current target skill before proposing changes.
- Classify the signals: process gap, validation gap, source drift, platform drift, user preference, candidate idea, incident, routing gap, or content bloat.
- Design the case set: incident, candidate rule, regression case, boundary case, and optional holdout challenge.
- Pass the generalization gate. A one-off incident does not automatically deserve a lasting rule.
- Map route impact. Remove weak routes and move machine-checkable facts to tools, tests, schema checks, diffs, validators, or files.
- Choose the net-improvement shape:
no_change,maintenance_note_only,prune_or_consolidate,local_refactor,cross_reference_refactor,major_refactor, ordeprecate_or_replace_source. - Produce the concrete plan and stop.
- Apply only after explicit approval.
- Validate, report what changed, and record follow-up risks.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 306 B
- evals/evals.json 5.4 KB
- references/evidence-and-scope.md 2.2 KB
- references/examples.md 2.3 KB
- references/upgrade-decision-protocol.md 2.1 KB
- references/validation-and-regression.md 2.7 KB
- scripts/test_validate_upgrade_artifacts.py 5.7 KB runs code
- scripts/validate_upgrade_artifacts.py 14 KB runs code
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.
- 13d ago First seen · 134 lines · 91 tokens per session scan A 91b497fbd165
run-history-skill-upgrader is a skill published in the GitHub repository dongshuyan/compass-skills (725 stars, last pushed 17d ago), licensed MIT. It adds 91 tokens to every session and 1,407 once invoked, about $0.0005 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
install-memu
Install or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and follow it to wire (or unwire) both seams (record and inject). Use when the user asks to install, set up, integrate, remove, or uninstall memU.
lore
Long-term Markdown project memory for AI coding agents. Use when the user wants to record, recall, audit, sync, or compress project decisions, architecture, conventions, monorepo scopes, or .lore/ entries, including natural-language requests like "remember this decision" or explicit lore…
fleet-conductor
Use when conducting a large backlog or multi-repository campaign across several worker lanes, especially when work needs bounded ownership, held dependencies, collision control, draft pull request gates, and evidence-based landing. Triggers on "conduct the fleet", "burn down the backlog", "run a multi-repo campaign"…
demi
Use before implementing, scaffolding, prototyping, or adding a feature when the work should start with the smallest useful code path, avoid speculative architecture, or prevent overbuilding before reduce would be needed.
stagiaire
Use when the current session needs an answer or a work product from a model on ANOTHER vendor's stack - a second opinion from a different model family, a cheap fast model for bulk work, or a cross-model review - by dispatching that vendor's own CLI as a one-shot worker. Triggers include "ask…
using-skillet
Use when starting any conversation - establishes how to find and use skillet skills, requiring skill invocation before ANY response including clarifying questions.