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 ArtemioPadilla/agent-triforce --skill traceabilitygit clone --depth 1 https://github.com/ArtemioPadilla/agent-triforceWrote 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/artemiopadilla/agent-triforce/traceability)<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/traceability"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/traceability/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/artemiopadilla/agent-triforce/traceability"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/traceability.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 | $0.00036 | $0.00974 |
| Opus 5 | $0.00018 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
traceability 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.
What it actually says
Generate a traceability matrix for a feature spec.
Input: The user provides a spec file path (e.g., docs/specs/auth-feature.md) or feature name.
Follow these steps:
SIGN IN:
- Run the SIGN IN checklist from your agent file
- Read the specified spec file
EXTRACT:
- Parse the spec for acceptance criteria in GIVEN/WHEN/THEN format
- Assign stable criterion IDs in format
{feature-id}-AC-{NNN}if not already present - Extract: criterion ID, criterion text, any referenced modules or components
TRACE:
4. For each acceptance criterion, scan src/ for implementation files:
- Search for comments referencing the criterion ID (e.g.,
Implements: {feature}-AC-001) - Fall back to keyword matching from criterion text (function names, module names)
- Use
tools/traceability.pyif available for automated scanning
- For each acceptance criterion, scan
tests/for test cases:- Search for explicit
Verifies: {criterion_id}references in test docstrings → mark as Explicit link - Fall back to keyword matching from criterion text → mark as Implicit link
- Extract
TC-{feature}-{NNN}test case IDs from matching test files
- Search for explicit
- For each acceptance criterion, scan
docs/reviews/for findings:- Search review files for references to the criterion or its subject
- Link findings by severity
BI-DIRECTIONAL VERIFICATION:
7. Scan tests/ for orphaned tests:
- Find all
TC-{feature}-{NNN}IDs andVerifies: {AC-ID}references across test files - Cross-reference against extracted criterion IDs
- Mark any test referencing a deleted or renamed AC as "Orphaned"
- Identify unlinked tests:
- Tests without any
Verifies:reference or TC-ID — may be valid infrastructure tests - List separately for human review
- Tests without any
GENERATE MATRIX:
9. Create the traceability matrix at docs/traceability/{feature-name}-matrix.md:
# Traceability Matrix: {Feature Name}
**Spec**: {spec_file_path}
**Generated**: {YYYY-MM-DD}
**Status**: {X covered / Y partial / Z missing}
| ID | Criterion | Implementation | Tests | Test IDs | Findings | Link Type | Status |
|----|-----------|---------------|-------|----------|----------|-----------|--------|
| {id} | {text} | {files} | {test files} | {TC-IDs} | {findings} | Explicit/Implicit/None | Covered/Partial/Missing |
## Coverage Summary
- **Explicit**: {N} ACs with direct TC-ID links
- **Implicit**: {N} ACs matched by keyword only
- **Uncovered**: {N} ACs with no test found
- **Orphaned tests**: {N} test references to non-existent ACs
- Status determination:
- Covered: has implementation file(s) AND at least one test with Explicit or Implicit link
- Partial: has implementation but no test, or has test but unclear implementation link
- Missing: no implementation or test found
TIME OUT — Traceability Verification (DO-CONFIRM):
- All acceptance criteria extracted from spec
- Criterion IDs assigned (stable, format:
{feature}-AC-{NNN}) -
src/scanned for implementation links -
tests/scanned for test coverage links (both TC-ID references and keyword matches) - Bi-directional check complete: orphaned tests identified, unlinked tests listed
-
docs/reviews/scanned for finding references - Each criterion has a status (Covered/Partial/Missing) and link type (Explicit/Implicit/None)
- Missing criteria flagged with
/generate-testsrecommendation
SIGN OUT:
9. Report matrix summary (covered/partial/missing counts)
10. If any criteria are Missing, suggest running /generate-tests on the relevant modules
11. Run the SIGN OUT checklist from your agent file
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 · 85 lines · 36 tokens per session scan A 96932551997a
traceability is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 974 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
warden
Use before opening a PR from a quest, once the code is written. Simulates a strict code reviewer by comparing changes against reference files and documented conventions, catching convention feedback before your human reviewer does.
java-best-practices
Java coding best practices. Use when writing or reviewing Java code (17+). Covers modern features, error handling, and patterns.
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.