Borrowing it
Nothing to install: this file belongs to davidmatousek/tachi. 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/davidmatousek/tachi/main/.claude/skills/tachi-orchestration/SKILL.mdgit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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/davidmatousek/tachi/tachi-orchestration)<a href="https://agentmods.dev/skills/davidmatousek/tachi/tachi-orchestration"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/tachi-orchestration/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/davidmatousek/tachi/tachi-orchestration"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/tachi-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.03201 |
| Opus 5 | $0.00044 | $0.01600 |
| Sonnet 5 | $0.00018 | $0.00640 |
| Haiku 4.5 | $0.00009 | $0.00320 |
Grade A, and why
tachi-orchestration 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 10d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tachi Orchestration Skill
Domain knowledge extracted from the tachi orchestrator agent to support the OWASP four-step threat modeling pipeline. This skill provides reference material that the orchestrator loads on-demand at specific workflow phases, keeping the agent definition focused on orchestration logic.
Domain Coverage
This skill contains six categories of domain knowledge:
-
Format Detection -- Input format recognition patterns for ASCII, Free-text, Mermaid, PlantUML, and C4 architecture descriptions with priority ordering and heuristic matching rules.
-
DFD Classification -- DFD element type classification signals for External Entity, Process, Data Store, and Data Flow with ambiguous-classification defaults and format-specific extraction guidance.
-
Trust Boundaries -- Format-specific boundary notation for Mermaid subgraph, ASCII dashes, PlantUML boundary, C4 boundaries, and Free-text prose markers.
-
Dispatch Rules -- STRIDE-per-Element normalization table mapping DFD element types to applicable threat categories, AI keyword dispatch rules with keyword-to-category mappings and matching semantics, dispatch table format specification, and the five correlation rules with detection algorithm and group assembly instructions.
-
Coverage Requirements & Matrix -- Required STRIDE+AI categories per component type (external-entity, process, data-store, data-flow, llm-process, mcp-server), category-to-agent mapping for targeted re-analysis, three-state coverage matrix cell model, deduplication rules, and footnote conventions.
-
Output & SARIF -- Output format specification for threats.md (frontmatter fields, all 7 required sections plus Section 4a), SARIF 2.1.0 generation specification with fingerprint preservation and taxonomy passthrough rules, structural validation checklist, and error handling templates.
Loading Table
| Reference File | Load Condition | Workflow Phase |
|---|---|---|
references/format-detection.md |
Entering Phase 1 (Format Identification) | Before determining architecture description format |
references/dfd-classification.md |
Entering Phase 1 (DFD Extraction) | Before classifying components into DFD element types |
references/trust-boundaries.md |
Entering Phase 1 (Boundary Identification) | Before extracting trust boundary notation |
references/dispatch-rules.md |
Entering Phase 2 (Determine Threats) | After Phase 1 component inventory is produced, before agent dispatch |
references/coverage-requirements.md |
Entering Phase 3 (Coverage Gate) | Before evaluating coverage completeness per component |
references/coverage-matrix-model.md |
Entering Phase 4 (Output Assembly) | Before building the coverage matrix in threats.md |
references/output-schemas.md |
Entering Phase 1 (Scope) for output format awareness; Phase 3 for table assembly; Phase 4 for validation | Before assembling Section 1, and before running the structural validation checklist |
references/sarif-specification.md |
Entering SARIF generation step in Phase 4 | After threats.md structural validation passes, before writing threats.sarif |
references/baseline-correlation.md |
Entering Phase 1a+ (Baseline Handling) | Before parsing baseline file, before carry-forward logic |
What ships with it
9 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.
- references/baseline-correlation.md 5.7 KB
- references/coverage-matrix-model.md 6.7 KB
- references/coverage-requirements.md 7.9 KB
- references/dfd-classification.md 5.6 KB
- references/dispatch-rules.md 30 KB
- references/format-detection.md 4.9 KB
- references/output-schemas.md 43 KB
- references/sarif-specification.md 40 KB
- references/trust-boundaries.md 5.3 KB
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.
- 10d ago First seen · 216 lines · 88 tokens per session scan A df0172d58efc
tachi-orchestration is a skill published in the GitHub repository davidmatousek/tachi (91 stars, last pushed 28d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,201 once invoked, about $0.0004 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
usap-program-manager
Security program manager and passive lifecycle orchestrator (cs-security-program-manager). Use for security roadmap planning, program health scanning, debt tracking, facilitated reviews, or when the user says "security roadmap", "program planning", "security debt", "proactive scan", or "program review".
usap-ciso
CISO and executive security advisor (cs-ciso-advisor). Use for board reports, executive risk briefings, regulatory gap assessments, cyber insurance inputs, or when the user says "board report", "CISO brief", "executive summary", "risk posture for leadership", or "regulatory update".
usap-incident-responder
Active incident command and response (cs-incident-responder). Use when there is a confirmed or suspected active incident, for containment decisions, forensic investigation, SEV declaration, or when the user says "declare incident", "start IR", "we have an active breach", or "forensics".
usap-red-teamer
Offensive security coordinator (cs-red-teamer). Use for red team campaign planning, attack path analysis, engagement scoping, adversary simulation, or when the user says "red team", "pentest", "attack simulation", "run an engagement", or "offensive security". Requires explicit authorization scope.
usap-alex
Universal USAP security advisor (cs-security-analyst). Use for any security question, alert triage (AT), threat hunt (TH), compromise assessment (CA), or when the user says "activate Alex", "start USAP", or asks what USAP can do.
nuclei
Nuclei CLI parameter reference and usage patterns - YAML-template vulnerability scanning, target input modes, template filters, output formats, rate limits, ProjectDiscovery dashboard upload, and common scan commands.