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 arozumenko/sdlc-skills --skill delivery-monitorgit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/delivery-monitor)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/delivery-monitor"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/delivery-monitor/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/arozumenko/sdlc-skills/delivery-monitor"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/delivery-monitor.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 | $0.00150 | $0.01253 |
| Opus 5.5 | $0.00060 | $0.00501 |
| Sonnet 5.5 | $0.00030 | $0.00251 |
| Haiku 4.5 | $0.00015 | $0.00125 |
Grade A, and why
delivery-monitor 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 16d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delivery-monitor — cycle time, cadence, estimate vs actual
tokenomics answers what did it cost; this skill answers how long did it
take and how did that compare with what we said. It never estimates, never
defaults a missing number, and labels every proxy as a proxy.
Quick start
# 1. Register the plan BEFORE the first dispatch (the tech-lead's plan file carries a ```json delivery-plan block). Inside Claude
# Code this also binds the calling session (subagents included) to the run — prints `SESSION claude:<id> -> <run>`.
node .claude/skills/delivery-monitor/scripts/delivery.mjs plan register --from docs/superpowers/plans/<plan>.md --id reg-1
# 2. The orchestrating session must be bound before it dispatches: the hook records dispatches only for a bound session (or one
# whose branch maps to exactly one item of exactly one open run). A session that did not register the plan binds itself:
node .claude/skills/delivery-monitor/scripts/delivery.mjs session set sec/run-1 # host/session default to CLAUDE_CODE_SESSION_ID
# Record transitions as they happen. A hook dispatch credited to the wrong item is withdrawn, then re-recorded:
node .claude/skills/delivery-monitor/scripts/delivery.mjs retract --agent <agent id> --plan sec/run-1 [--dry-run] # or --observation <id>
node .claude/skills/delivery-monitor/scripts/delivery.mjs event TASK-023 done --sha <merge-sha> --id done-023
node .claude/skills/delivery-monitor/scripts/delivery.mjs event G12 done --sha <landing-sha> --id land-g12 # mission landing
node .claude/skills/delivery-monitor/scripts/delivery.mjs event INFRA-2 done --id done-infra-2 # landed no commit (infra, QA run, gate): no --sha, stamped now
# 3. Fill in history that predates the ledger
node .claude/skills/delivery-monitor/scripts/delivery.mjs backfill --git --plan sec/run-1 --head <sha>
# GitHub-merged work (squash/merge-commit PRs, task PRs into a mission branch): read merged PRs via gh, or offline from JSON
node .claude/skills/delivery-monitor/scripts/delivery.mjs backfill --pr --plan sec/run-1 [--from-json prs.json] [--since <iso>] [--dry-run]
# 4. Optional: automatic dispatch start/end on Claude Code (+ shared telemetry submodule)
node .claude/skills/delivery-monitor/scripts/install-hooks.mjs # --remove undoes, --doctor checks
# 5. Read
node .claude/skills/delivery-monitor/scripts/delivery.mjs status
node .claude/skills/delivery-monitor/scripts/delivery.mjs report [--json] [--html] [--from-json <f>] [--since 2026-09-01] [--level task] [--class M]
node .claude/skills/delivery-monitor/scripts/delivery.mjs report --html --out delivery.html
What ships with it
50 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.
- fixtures/plan-markdown/tasks-excerpt.md 2.0 KB
- fixtures/plan-markdown/tasks-v2-execution-plan.md 8.0 KB
- fixtures/security-testing/build-fixture-repo.mjs 2.8 KB runs code
- fixtures/security-testing/dataset.json 15 KB
- fixtures/security-testing/extract-dataset.mjs 2.9 KB runs code
- fixtures/security-testing/golden.json 480 B
- hooks/dispatch-hook.mjs 17 KB runs code
- hooks/dispatch-hook.test.mjs 27 KB runs code
- README.md 6.6 KB
- references/event-model.md 14 KB
- references/factory-roles.json 572 B
- references/metrics.md 10 KB
- references/plan-block.md 14 KB
- references/spike-1.md 1.6 KB
- scripts/delivery.mjs 41 KB runs code
- scripts/delivery.test.mjs 62 KB runs code
- scripts/golden.test.mjs 4.0 KB runs code
- scripts/install-hooks.mjs 18 KB runs code
- scripts/install-hooks.test.mjs 20 KB runs code
- scripts/installed.test.mjs 4.7 KB runs code
- scripts/lib/associate.mjs 2.7 KB runs code
- scripts/lib/associate.test.mjs 6.7 KB runs code
- scripts/lib/events.mjs 12 KB runs code
- scripts/lib/events.test.mjs 15 KB runs code
- scripts/lib/git-backfill.mjs 8.1 KB runs code
- scripts/lib/git-backfill.test.mjs 11 KB runs code
- scripts/lib/git-fixtures.mjs 4.2 KB runs code
- scripts/lib/git.mjs 2.4 KB runs code
- scripts/lib/git.test.mjs 2.4 KB runs code
- scripts/lib/metrics.mjs 19 KB runs code
- scripts/lib/metrics.test.mjs 24 KB runs code
- scripts/lib/paths.mjs 4.9 KB runs code
- scripts/lib/paths.test.mjs 3.4 KB runs code
- scripts/lib/plan-markdown.mjs 4.4 KB runs code
- scripts/lib/plan-markdown.test.mjs 4.6 KB runs code
- scripts/lib/plan.mjs 16 KB runs code
- scripts/lib/plan.test.mjs 15 KB runs code
- scripts/lib/pr-backfill.mjs 7.4 KB runs code
- scripts/lib/pr-backfill.test.mjs 9.8 KB runs code
- scripts/lib/report.mjs 55 KB runs code
- scripts/lib/report.test.mjs 48 KB runs code
- scripts/lib/roster.mjs 2.2 KB runs code
- scripts/lib/roster.test.mjs 1.4 KB runs code
- scripts/lib/sync.mjs 2.9 KB runs code
- scripts/lib/sync.test.mjs 4.9 KB runs code
- scripts/lib/timeline.mjs 18 KB runs code
- scripts/lib/timeline.test.mjs 32 KB runs code
- templates/delivery-plan.template.json 1.1 KB
- templates/plan-block.template.md 3.8 KB
- templates/profile.template.json 248 B
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.
- 16d ago Changed · +1 lines 60fbc9c0994f
- 16d ago Changed · +9 lines c2468f5cc581
- 18d ago Changed · +7 lines 9ea29a3e73b4
- 1mo ago First seen · 39 lines · 150 tokens per session scan A 8bec926f2dff
delivery-monitor is a skill published in the GitHub repository arozumenko/sdlc-skills (25 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 1,253 once invoked, about $0.0006 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 2026-09-19.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
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…