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 Morningstar202604/awesome-skillkit --skill self-evalgit clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitWrote 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/morningstar202604/awesome-skillkit/self-eval)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/self-eval"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/self-eval/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/morningstar202604/awesome-skillkit/self-eval"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/self-eval.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 | $0.00102 | $0.02282 |
| Opus 5.5 | $0.00041 | $0.00913 |
| Sonnet 5.5 | $0.00020 | $0.00456 |
| Haiku 4.5 | $0.00010 | $0.00228 |
Grade A, and why
self-eval 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Eval: Honest Work Evaluation
Produces an honest, calibrated work assessment. It replaces the AI default of "give everything a 4" with a structured two-axis score, forced devil's-advocate reasoning, and cross-session anti-inflation detection.
Core insight: AI self-evaluation converges on "everything is a 4" because a single axis conflates task difficulty with execution quality. self-eval splits the two axes apart, then combines the score using a fixed matrix the model cannot override.
Input Checklist
| Input | Required | Description |
|---|---|---|
| Context to evaluate | Yes | Work completed in the current session, or a specific task passed via /self-eval <description> |
| Historical scores file | No | .self-eval-scores.jsonl in the working directory; used for the anti-inflation check if present |
When something is missing, ask for it all at once:
"Please provide: (1) the work to evaluate (default = what was completed in this session; you can use /self-eval to specify); (2) whether to compare against historical scores across sessions (default reads .self-eval-scores.jsonl; skip if none). Once confirmed, I'll start."
Pre-flight Checks
- This skill is pure prompt-driven with no external dependencies; no tools need installing.
- The working directory is writable (used to append to
.self-eval-scores.jsonl):test -w .→ writable; otherwise only output the evaluation, skip persistence, and say so. - If the user passes
$ARGUMENTSor/self-eval <content>, use that content as the evaluation target; otherwise review the entire session history, first summarizing this session's outcome in one sentence before scoring.
Workflow
Step 1: Identify and summarize the work
Action: identify completed work from the session history (or passed arguments) and summarize it in one sentence.
Expected: produce a single-line Task summary.
On failure: the history is empty or cannot be determined → ask the user to explicitly specify the evaluation target with /self-eval <description>.
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 Changed · -3 tokens per session 95d9dc854eec
- 1mo ago Changed · -25 lines · +54 tokens per session 7694a61e7456
- 1mo ago First seen · 186 lines · 51 tokens per session scan A 0b829818fd15
self-eval is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (0 stars, last pushed 25d ago), licensed Apache-2.0. It adds 102 tokens to every session and 2,282 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.