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 selectess/fde-consultants-protocoles --skill template-skillgit clone --depth 1 https://github.com/selectess/fde-consultants-protocolesWrote 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/selectess/fde-consultants-protocoles/template-skill)<a href="https://agentmods.dev/skills/selectess/fde-consultants-protocoles/template-skill"><img src="https://agentmods.dev/badge/skills/selectess/fde-consultants-protocoles/template-skill/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/selectess/fde-consultants-protocoles/template-skill"><img src="https://agentmods.dev/badge/skills/selectess/fde-consultants-protocoles/template-skill.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 | $0.00031 | $0.00731 |
| Opus 5 | $0.00015 | $0.00365 |
| Sonnet 5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
template-skill 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 9d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
My Skill Name
Use this as a starting point for any new FDE Consultant Skill. Copy this folder, rename it, and customize the content.
Description
[1 paragraph: what this skill does, when to use it, what problem it solves]
When to use this skill
Activate this skill when the user:
- [Trigger 1: explicit mention of the skill name]
- [Trigger 2: task matches the skill's domain]
- [Trigger 3: project type matches the skill's target]
What this skill produces
[1 paragraph: what artifacts the skill generates, what quality bar]
Operating Principles (subset relevant to this skill)
- [Principle 1 — pick from skill/SKILL.md 14 OP]
- [Principle 2]
- [Principle 3]
Anti-Patterns to avoid
- [Anti-pattern 1]
- [Anti-pattern 2]
- [Anti-pattern 3]
Workflow
- Stage 1 — Scoping: [what to do]
- Stage 2 — Prototyping: [what to do]
- Stage 3 — Production: [what to do]
- Stage 4 — Feedback: [what to do, end with FDE Assurance Score]
Examples
Example 1: [use case]
[input -> output]
Example 2: [use case]
[input -> output]
Templates
This skill uses these templates (in skill/templates/):
scoping-report.md— Stage 1 outputprototype-spec.md— Stage 2 outputproduction-handoff.md— Stage 3 outputproductization-memo.md— Stage 4 output
Tools (Python)
This skill uses these scripts (in skill/scripts/):
decompose_problem.py— validate 6-Qroi_calculator.py— compute ROIscientific_search.py— held-out promotion gateevals_runner.py— 6-trait scoringontology_extractor.py— Palantir-style ontology
References (loaded on demand)
In skill/references/:
fde-methodology.md— core methodologyfde-trust-score.md— FDE Assurance Score formulafde-skeptical-deployment.md— gate protocol
FDE Assurance Score
This template applies its own FDE Assurance Score:
| Component | Max | Actual |
|---|---|---|
| Claim (falsifiable) | 25 | 25 (a template by definition is verifiable) |
| Contradiction (failure modes) | 25 | 20 (acknowledged: customization risk) |
| Evidence trail | 30 | 25 (cross-references to canonical docs) |
| Anti-patterns clean | 20 | 18 (no fake metrics) |
| TOTAL | 100 | 88/100 → Certified |
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.
- 9d ago First seen · 103 lines · 31 tokens per session scan A eb0ba2709737
template-skill is a skill published in the GitHub repository selectess/fde-consultants-protocoles (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 731 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 2026-08-31.
Other skills, from other repositories
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
loop-orchestration
Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.
loop-operator-context
Advisory operating context for the loop-orchestration example.
nitrosend
Operate a Nitrosend account through one governed Runx skill: inspect readiness, analytics, subscription plans, and purchase status; plan and apply campaign/flow/template/segment drafts; import consented contacts; and approve or deliver email operations with provider readback.
issue-intake
Turn a noisy inbound request into a bounded intake artifact and an explicit next runx lane.