What is traceability-gate?

A traceability check for requirements and related project documents. Traceability means each newer document must point to the requirement or decision it came from.

Use it before pull requests, after batches that derive security or non-functional requirements, and when promoting experimental skills into regular use.

It stops unlinked requirements from quietly entering the project, while making clear that a linked requirement may still be poorly written.

traceability-gate — Skill for Claude Code and Codex by andreaswasita

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojo

agentmods

npx agentmods add skills/andreaswasita/copilot-agents-dojo/traceability-gate

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/traceability-gate/github.svg)](https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/traceability-gate)

Your own site

<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/traceability-gate"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/traceability-gate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/traceability-gate"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/traceability-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,248 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00014	$0.01248
Opus 5.5	$0.00006	$0.00499
Sonnet 5.5	$0.00003	$0.00250
Haiku 4.5	$0.00001	$0.00125

Measured 2mo ago against content hash 5d1f9ca8b826, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

traceability-gate 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.

skills/traceability-gate/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Traceability Gate

The single governance gate for the TOGAF red thread: no artifact at layer N+1 may persist unless it carries a verified link to a parent at layer N. The skill does NOT elicit requirements and does NOT derive new ones; its only job is to refuse to let unlinked artifacts live.

When to Use

Before any pull request that touches requirements/** or any skill that emits artifacts under it.
Before promoting a curator-proposed skill from optional-skills/ to skills/ — learned skills must pass the same gate as live delivery.
During Phase B → C and Phase C → D transitions, to prove the cascade is intact before architecture commits to a design.
After every batch run of derive-nfr-from-driver or derive-security-from-risk.
NOT as a substitute for elicitation — the gate verifies linkage, not quality of requirements. A bad requirement linked to a bad parent still passes the gate.

Prerequisites

The engagement directory exists at requirements/<engagement>/.
spec/artifact-schema.md defines the frontmatter contract.
scripts/verify-traceability.sh is executable.

The gate is allowed to be called against an empty engagement directory — it reports zero artifacts and exits 0. That is the seed state, not a failure.

How to Run

# Full traceability check for one engagement
bash scripts/verify-traceability.sh requirements/<engagement>

# CI / strict mode — warnings (e.g. unratified) become failures
bash scripts/verify-traceability.sh --strict requirements/<engagement>

# Generate the RTM as a byproduct of the gate
bash scripts/gen-rtm.sh requirements/<engagement>

# Roll the gate into the dojo-wide gate
bash scripts/verify.sh        # invokes run_traceability_checks

Quick Reference

Action	Tool	Notes
Run gate locally	`bash scripts/verify-traceability.sh requirements/<engagement>`	Exit 0 = lineage intact.
Run gate strict	`bash scripts/verify-traceability.sh --strict …`	CI default.
Regenerate RTM	`bash scripts/gen-rtm.sh requirements/<engagement>`	Writes `docs/rtm-<engagement>.md`.
Full dojo gate	`bash scripts/verify.sh`	Includes the traceability check.

Read the full file on GitHub · 131 lines

Changes

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 · 131 lines · 14 tokens per session scan A 5d1f9ca8b826

Subscribe to this mod's changes

traceability-gate is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (54 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,248 once invoked, about $0.0001 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 2026-08-30.

Planning agent-governance agentic-ai ai-coding copilot-agents copilot-instructions copilot-skills discipline gate governance togaf traceability

traceability-gate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
traceability-gateandreaswasita/copilot-agents-dojo	Skill	54	2mo ago	MIT	A	14	Claude Code, Codex
complianceericrisco/rsc-harness	Skill	503	2d ago	MIT	A	96	Claude Code, Codex
decision-ledgerjohnrucnapier-sketch/ACGM-for-Claude-Code	Skill	1	1mo ago	none	A	99	Claude Code
governance-bootstrapjohnrucnapier-sketch/ACGM-for-Claude-Code	Skill	1	1mo ago	none	A	107	Claude Code
session-groundingjohnrucnapier-sketch/ACGM-for-Claude-Code	Skill	1	1mo ago	none	A	51	Claude Code
truth-firstjohnrucnapier-sketch/ACGM-for-Claude-Code	Skill	1	1mo ago	none	C	120	Claude Code
managing-mcp-serversJetBrains/thinkrail	Skill	7.8k	yesterday	Apache-2.0	A	62	Claude Code, Codex