Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add postindustria-tech/agentic-toolkit/plugin install pm-practicesWrote 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/postindustria-tech/agentic-toolkit/requirements-coverage-audit)<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/requirements-coverage-audit"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/requirements-coverage-audit/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/postindustria-tech/agentic-toolkit/requirements-coverage-audit"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/requirements-coverage-audit.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 | $0.00093 | $0.02434 |
| Opus 5.5 | $0.00037 | $0.00974 |
| Sonnet 5.5 | $0.00019 | $0.00487 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
requirements-coverage-audit 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements coverage audit
Compare the delivery plan against the supplied scope and produce traceable findings for PM decisions. Read-only: do not write to Jira, create/refine tickets, generate implementation tasks, score ticket quality, verify implementation, or rewrite scope.
Inputs
Accept paths and source-role assignments in ordinary language or invocation arguments:
--scope PATH: authoritative requirements, repeatable; required source role.--plan PATH(or--sow PATH): optional document milestone/task plan.--jira-export PATH: optional Jira search JSON/page files and companion details.--jira-jql QUERYor--jira-filter ID: optional authorized live Jira scope.--jira-milestones MAPPING: epic, release/version, or explicit issue-set mapping; accept ordinary-language assignments, not a fixed schema or epic assumption.--old-sow PATH: optional historical version, repeatable with its version/order.--supporting PATH: optional requirements, architecture, or recorded decisions.--exclusions PATH: optional exclusions or future-scope source.--milestone NAME: optional selection; default is all milestones.--output DIR: optional persistent private directory. Without it, write to a new timestamped directory under the system temporary directory and say that it is temporary. Honor a user-chosen directory only after checking it is not tracked or exposed to version control; do not modify ignore rules to make it so. Resolve the primary plan if several exist.
These are interpretation conventions, not an executable CLI or a project config. Require authoritative scope and at least one delivery-plan source; one document can fill several roles. Infer milestone names/count and relevant sections from its contents; do not require a particular appendix, heading, domain, or historical version. Preserve original milestone names in reports. Resolve an ambiguous selection before analyzing it.
For Jira input, read references/jira-matching.md before retrieval or assessment. Document-only runs do not contact Jira. Confirm project/filter, milestone mapping, hierarchy, selection and available context; do not silently change the configured account/site or assume an epic is a milestone.
What ships with it
13 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.
- evals/evals.json 8.7 KB
- evals/fixtures/harbor-sow.md 1.3 KB
- evals/fixtures/jira/details-8.json 461 B
- evals/fixtures/jira/incomplete-snapshot.md 1.4 KB
- evals/fixtures/jira/page-1.json 8.0 KB
- evals/fixtures/jira/page-2.json 4.0 KB
- evals/fixtures/jira/scope.md 1.0 KB
- evals/fixtures/jira/snapshot.md 1.0 KB
- evals/procedure.md 5.0 KB
- evals/results-pm-275.md 7.6 KB
- evals/results.md 4.6 KB
- references/jira-matching.md 6.4 KB
- references/report-shapes.md 4.9 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 · 217 lines · 93 tokens per session scan A 850528585cc4
requirements-coverage-audit is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 93 tokens to every session and 2,434 once invoked, about $0.0004 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 2026-10-06.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…