Borrowing it
Nothing to install: this file belongs to tternquist/marklogic-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tternquist/marklogic-mcp/master/.claude/skills/semaphore-classification-tuning/SKILL.mdgit clone --depth 1 https://github.com/tternquist/marklogic-mcpWrote 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/tternquist/marklogic-mcp/semaphore-classification-tuning)<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/semaphore-classification-tuning"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/semaphore-classification-tuning/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/tternquist/marklogic-mcp/semaphore-classification-tuning"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/semaphore-classification-tuning.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 | $0.00117 | $0.01789 |
| Opus 5.5 | $0.00047 | $0.00716 |
| Sonnet 5.5 | $0.00023 | $0.00358 |
| Haiku 4.5 | $0.00012 | $0.00179 |
Grade A, and why
semaphore-classification-tuning 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 2mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semaphore Classification Tuning
The three fix levels — always try them in order
| Level | Tool | Scope | Use when |
|---|---|---|---|
| 1. Labels | semaphore_concept_labels_update |
one concept | a specific concept fires wrongly or misses |
| 2. Threshold | semaphore_classify(threshold=…) |
one query | exploring precision/recall without changing the model |
| 3. Template | semaphore_kid_template_set |
every concept | the same scoring problem affects all concepts |
The decisive question: is the problem with one concept or with scoring behaviour?
A .kid template applies identically to every concept in the model — a weight
change moves all concepts equally. That makes it the right fix for systemic problems
and the wrong fix for a misbehaving concept.
Practical trigger for reaching for level 3: you find yourself wanting to make the same label edit to many concepts for the same reason. That reason is a scoring behaviour that belongs in the template.
Every change at any level requires semaphore_publish before it takes effect, then
semaphore_classify to verify.
Symptom → action
Full step-by-step playbooks for all eight symptoms are in
references/symptom-playbooks.md. Summary:
| Symptom | Most likely cause | First move |
|---|---|---|
false_positives |
over-broad altLabel; nearlist on scattered words | inspect labels (semaphore_concept_get) |
missing_matches |
missing synonyms; threshold too high | add altLabels; drop threshold to 0 to see raw scores |
score_too_uniform |
evidence types weighted too evenly | raise phraselist_weight, lower nearlist_weight |
hierarchy_not_firing |
lower_hierarchy_weight too low, or no skos:broader links |
verify hierarchy exists, then preset=hierarchy_heavy |
nearlist_noise |
multi-word labels matching scattered constituents | lower nearlist_weight, or preset=precision |
short_text_poor |
default weights assume long documents | preset=short_text |
zone_ignored |
no zone-biasing configured | set title_weight / body_weight |
associative_overfiring |
related-concept score propagation | associative_cap=0 |
What ships with it
1 file 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.
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.
- 2mo ago First seen · 139 lines · 117 tokens per session scan A eebf05b943d2
semaphore-classification-tuning is a skill published in the GitHub repository tternquist/marklogic-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,789 once invoked, about $0.0005 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.
semaphore-classification-tuning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| semaphore-classification-tuningtternquist/marklogic-mcp | Skill | 4 | 1mo ago | MIT | A | 117 | Claude Code |
| debug-inferenceNVIDIA/OpenShell | Skill | 21k | yesterday | Apache-2.0 | A | 120 | Claude Code, Codex |
| notebooklmteng-lin/notebooklm-py | Skill | 20k | 2d ago | MIT | A | 79 | Claude Code, Codex |
| oh-my-poshJanDeDobbeleer/oh-my-posh | Skill | 24k | 2d ago | MIT | A | 47 | Claude Code, Codex |
| spark-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 75 | Claude Code |
| rocketride-debugging-pipelinesrocketride-org/rocketride-server | Skill | 20k | yesterday | MIT | A | 67 | Claude Code, Codex |
| autorag-doctorMarker-Inc-Korea/AutoRAG | Skill | 5.3k | yesterday | Apache-2.0 | A | 144 | Claude Code, Codex |