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 uqeu/estelle-cli --skill estellegit clone --depth 1 https://github.com/uqeu/estelle-cliWrote 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/uqeu/estelle-cli/estelle)<a href="https://agentmods.dev/skills/uqeu/estelle-cli/estelle"><img src="https://agentmods.dev/badge/skills/uqeu/estelle-cli/estelle/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/uqeu/estelle-cli/estelle"><img src="https://agentmods.dev/badge/skills/uqeu/estelle-cli/estelle.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 | $0.00089 | $0.02509 |
| Opus 5.5 | $0.00036 | $0.01004 |
| Sonnet 5.5 | $0.00018 | $0.00502 |
| Haiku 4.5 | $0.00009 | $0.00251 |
Grade A, and why
estelle 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 27d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estelle
Estelle answers from the real, indexed repository and refuses what it cannot verify. Navigation and
verify run with no model call, so they cannot be argued into agreeing with you.
1 · Is Estelle actually here?
Look at your own tool list before following anything below.
estelle_*/find_definition/gate/verifypresent -> Estelle is wired. Use it as written.- None present -> say so once: "Estelle isn't connected here, so I can't ground this —
https://api.fatelabs.ca/mcp." Mark every repo claim unverified and stop following this file.
2 · Pull the memory. This is your first action.
Estelle saves automatically — hooks checkpoint every session. Estelle does not hand it back. Per-turn context push is OFF; you pull.
Call estelle_resume before you plan anything. Then memory_chat when the user says "we decided",
"last time", "you said"; list_sessions -> get_session for a specific one.
A session that never pulled is a session that re-decided what the team already decided. Measured 2026-09-19: 73 saved records went unread for hours while the model searched the filesystem.
A citation is the answer. If recall returns one, use it. Never reply "I'd rather check the repo" while holding the quote.
Read cheap before you read deep. verify and the nav tools cost no model call — spend them first.
estelle_resume → memory_chat → get_session is cheapest-to-dearest; pulling a whole session to answer
what one citation already answers is the common waste.
3 · Route the question
| you were about to | do this instead |
|---|---|
Grep a pattern or symbol |
estelle_grep — searches the indexed repo in one call |
Glob for where something lives |
locate, or find_definition to go straight to the symbol |
Read a file to learn who calls something |
find_usages (symbol) · blast_radius (file) |
| guess a signature from its name | find_definition — names are stable, signatures drift |
| assert a symbol or API exists | verify |
| offer or apply a diff | gate, then review when correctness is arguable |
| ask what breaks / what depends on what | blast_radius, dependency_path, import_cycles |
| ask what we decided | estelle_resume, memory_chat, get_session |
| ask what's broken in production | monitor_issues, monitor_logs, monitor_alerts |
| ask if a library really has that API | research_ask |
| end or overflow a session | estelle_checkpoint |
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.
- 27d ago First seen · 169 lines · 89 tokens per session scan A f673eeeb26b2
estelle is a skill published in the GitHub repository uqeu/estelle-cli (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,509 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 2026-09-20.
Other skills, from other repositories
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
autofix
Review and repair current local changes until they converge, or run Qwen Code Autofix issue and review workflows from GitHub Actions.
tilth
Use the tilth CLI for code reading, outlining, search, callers, blast-radius deps, and structural diffs. Activate when the user asks to explore a repo, find a symbol, trace callers, read a file, view a diff, or analyze impact. Prefer tilth over grep/cat/find/ls — one invocation returns AST-aware outlines, definitions…
audit
Fast quality gate — detects stack, runs static analysis, checks cross-layer consistency, fixes issues. Run between every pipeline phase, before every commit push, after every feature batch. Lighter than /analyze but catches the same critical issues.
logic-lens
AI-powered Claude Code skill that performs deep code review using formal logic and reasoning frameworks to detect bugs, anti-patterns, and security risks beyond what linters catch.
fix
Resolve blocking review gaps through bounded repairs and independent re-review; diagnose stalled attempts without expanding scope.