Agent skill

Sdlc Review

by NousResearch in NousResearch/hermes-agent

Review Kanban handoffs and route verified outcomes. An agent skill from NousResearch/hermes-agent.

MITAuto-check passedProductivity & Automation

Install Sdlc Review

skills CLI
$ npx skills add NousResearch/hermes-agent --skill sdlc-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NousResearch/hermes-agent sdlc-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NousResearch/hermes-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/devops/sdlc-review .claude/skills/sdlc-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sdlc-review
GitHub stars
252k
Token cost
~2.3k tokens
SKILL.md length
1,126 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Review Kanban handoffs and route verified outcomes. An agent skill from NousResearch/hermes-agent.

  • Works in 4 steps: Orient from the durable task record → Compare requested behavior with… → Choose one verdict → …
  • Tasks that involve Task management
  • SKILL.md covers When to Use, Prerequisites, How to Run and Quick Reference, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sdlc Review is an agent skill from NousResearch/hermes-agent. Review Kanban handoffs and route verified outcomes.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Task management. The repository describes itself as: The agent that grows with you. The licence is MIT.

When your agent uses it

  • Tasks that involve Task management

Example prompts

  • “/sdlc-review”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Orient from the durable task record
  2. Compare requested behavior with delivered behavior
  3. Choose one verdict
  4. Preserve role separation

What it can do on your machine

Read from SKILL.md and the folder at commit dce1e9b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sdlc Review loads about 2.3k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 1,126 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NousResearch/hermes-agent at commit dce1e9b, republished under its MIT licence (© NousResearch). 1,126 words, ~2,267 tokens.

Download SKILL.mdSave it as .claude/skills/sdlc-review/SKILL.md (or your agent's skills folder).
name
sdlc-review
description
Review Kanban handoffs and route verified outcomes.
version
1.1.0
author
Jakub Wolniewicz (@frizikk) + Hermes Agent
license
MIT
platforms
linux, macos, windows
environments
kanban

SDLC Review Skill

Independently verify work handed from a Kanban implementation run to the review lane, then approve it, request changes, or escalate. This skill reviews the deliverable and its evidence; it does not take over the implementer's work.

When to Use

Use this skill when all of the following are true:

  • the dispatcher spawned you for a task claimed from the review lane;
  • an implementer submitted a review_requested handoff;
  • the task needs an independent verdict before it can be completed.

Do not use it for a separate downstream review card. A downstream card is ordinary implementation work with a review-oriented specification and completes through its own lifecycle.

Prerequisites

  • A Kanban worker context with the current task and run identifiers.
  • Native Kanban tools: kanban_show, kanban_comment, kanban_complete, kanban_request_changes, and kanban_block.
  • Workspace access through read_file, search_files, and terminal when the deliverable is code.
  • The task's original specification, acceptance criteria, handoff summary, and prior run history must be available through kanban_show.

How to Run

This skill is loaded automatically by the review dispatcher. Start with kanban_show before inspecting files or choosing a verdict.

  1. Read the task specification and the latest review_requested handoff.
  2. Inspect the actual deliverable and run relevant verification.
  3. Choose exactly one verdict: approve, request changes, or escalate.
  4. Record concrete evidence in the terminal Kanban transition.

Quick Reference

VerdictWhenFinal action
ApproveAcceptance criteria and verification passkanban_complete
Request changesCorrectable implementation defects remainkanban_comment, then kanban_request_changes
EscalateA human decision or external prerequisite is requiredkanban_block

A requested-changes transition returns the task to its original implementer. When that implementer requests review again without naming a reviewer, the persisted reviewer provenance routes the re-review back to the same reviewer profile.

Review Lenses

Vary how you look at the work on each round instead of repeating the same inspection. Decorrelated lenses catch different defect classes: a cold read of the artifact surfaces design and correctness problems that the implementer's narrative would have framed away, execution surfaces claims that do not reproduce, and a strict contract audit surfaces quiet scope drift. Repeating the round-1 lens on round 3 mostly re-finds what round 1 already found.

Determine the current round from the history the task record already gives you: count the changes_requested entries in the "Prior attempts on this task" section of your worker context (also visible as prior runs in kanban_show). The current review round is that count plus one. Round 1 therefore shows zero changes_requested attempts; round 2 shows one; and so on.

RoundLensHow to apply it
1ArtifactRead the diff or deliverable cold, before the implementer's summary. Form an independent judgment, then compare it against the handoff narrative and investigate every mismatch.
2ExecutionCheck out the work and actually run it via terminal: build, test, and exercise the reported behavior yourself. Verify each handoff claim empirically instead of re-reading the artifact.
3+ContractRe-read the ORIGINAL task body and acceptance criteria, then audit the deliverable strictly against them. Also verify that every item from every prior kanban_request_changes round actually landed.

The baseline duties in the Procedure section still apply on every round; the lens sets which inspection you lead with and weight most heavily.

Lens variation for ad-hoc review fan-outs

The same principle applies outside the Kanban review lane. When spawning multiple parallel reviewers via delegate_task, give each reviewer a different lens — one diff-only brief, one full-context brief, one checkout-and-run brief — rather than identical briefs. Identical briefs produce correlated verdicts and duplicate findings; varied briefs cover more defect classes for the same review spend.

Procedure

1. Orient from the durable task record

Call kanban_show and identify:

  • the original task body and acceptance criteria;
  • the latest implementation summary and structured metadata;
  • changed files, commit identifiers, and test evidence;
  • comments and decisions from earlier runs;
  • findings from prior review rounds.

Treat the handoff as a claim to verify, not as proof that the work is correct.

Show full SKILL.md (475 more words)Show less
2. Compare requested behavior with delivered behavior

Map every acceptance criterion to concrete implementation or output evidence. Note omissions, changed semantics, and unrelated scope before deciding whether to run deeper checks.

For code work:

  1. Use read_file and search_files to inspect the changed paths and their callers.
  2. Use terminal to inspect the diff and run the project's existing focused tests, lint, type checks, or build commands.
  3. Exercise the reported failure path and at least one ordinary control path when practical.
  4. Check error handling, edge cases, concurrency boundaries, data preservation, security boundaries, and cross-platform behavior relevant to the change.
  5. Confirm that tests assert behavior rather than merely snapshotting source text or constants.

For non-code work:

  1. Inspect the complete deliverable rather than only its summary.
  2. Check correctness, completeness, formatting, and provenance.
  3. Validate referenced URLs or external facts with the appropriate native tools when they affect the verdict.
3. Choose one verdict
Approve

Approve only when the acceptance criteria are satisfied and the evidence is sufficient. Call:

text
kanban_complete(
    summary="Reviewed and approved. <what was verified>",
    metadata={"review_outcome": "approved", "reviewer_checks": [...]}
)

Include the exact checks that passed and any bounded caveat that does not block acceptance.

Request changes

Use this for specific, correctable defects. First record actionable findings:

text
kanban_comment(
    task_id="<current-task-id>",
    body="Changes requested:\n1. <file or artifact + defect>\n2. <required correction>",
)

Then return the same task to its implementer:

text
kanban_request_changes(
    reason="<concise summary of the required corrections>"
)

State where the defect is, how it reproduces, why it violates the task, and what minimum outcome would resolve it. The transition does not use blocker recurrence accounting.

Escalate

Use escalation only when the reviewer and implementer cannot resolve the problem without a human decision or external prerequisite:

text
kanban_block(
    reason="escalation: <decision or prerequisite required>"
)

Explain the blocked decision and the smallest information needed to continue.

4. Preserve role separation

Do not edit the implementation while acting as reviewer. Request changes and let the implementer produce the next candidate; then independently verify that candidate in the next review run.

Pitfalls

  • Rubber-stamping: A passing handoff summary is not independent evidence.
  • Reviewer implementation: Editing the deliverable hides ownership and weakens the re-review boundary.
  • Vague findings: “Needs work” does not give the implementer a reproducible correction target.
  • Style-only blocking: Do not request changes for preference-level nits when behavior and repository standards are satisfied.
  • Skipping prior rounds: Re-review must confirm both the requested corrections and preservation of previously passing behavior.
  • Using blockers for ordinary rework: Correctable defects belong in kanban_request_changes; reserve kanban_block for genuine external blockers or human decisions.
  • Completing without evidence: Every approval summary must name the checks or artifacts actually inspected.

Verification

Before submitting the verdict, confirm:

  • kanban_show was read for the current task and run.
  • Every acceptance criterion was mapped to evidence.
  • The actual deliverable was inspected.
  • Relevant focused checks were run or an explicit reason was recorded when execution was impossible.
  • Prior requested changes were re-tested on re-review.
  • Unrelated regressions and scope changes were considered.
  • The verdict uses exactly one terminal action.
  • The summary contains concrete, non-secret evidence.
  • No implementation files were edited by the reviewer.

© NousResearch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/devops/sdlc-review of NousResearch/hermes-agent.

Open the folder on GitHubat commit dce1e9b

Compare with similar skills

Sdlc Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sdlc Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sdlc Review this skillNousResearch/hermes-agent252k—~2.3kAutomated safety check: PassMIT
Superset Agent Standupsuperset-sh/superset15k—~712Automated safety check: PassCustom licence
AgentRQ Workspace Agentagentrq/agentrq1.1k—~1.9kAutomated safety check: PassAGPL-3.0
Markdown Task Managerioniks/MarkdownTaskManager535—~2.2kAutomated safety check: PassMPL-2.0
Pi Messenger Crewnicobailon/pi-messenger719—~3.7kAutomated safety check: PassNone
Codekanban CLIfy0/CodeKanban226—~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Superset Agent Standup

    superset-sh/superset

    Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.

    15k GitHub stars~712 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Guides a workspace agent through executing assigned tasks, replying to a remote human operator, and creating sub-tasks, memory and events inside an AgentRQ workspace.

    1.1k GitHub stars~1.9k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Markdown Task Manager

    ioniks/MarkdownTaskManager

    A skill your agent uses when managing tasks, the system is a Kanban task manager based on local Markdown files (kanban.md and archive.md).

    535 GitHub stars~2.2k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed
  • Pi Messenger Crew

    nicobailon/pi-messenger

    Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination.

    719 GitHub stars~3.7k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Codekanban CLI

    fy0/CodeKanban

    Operate CodeKanban workflows, terminal sessions, and web sessions through the installable codekanban-cli command.

    226 GitHub stars~2.7k tokensUpdated 7 days ago
    Productivity & AutomationAuto-check passed
  • Kanban Video Orchestrator

    Luciole-Studio/Misaka-Agent

    Plan and run multi-agent video production pipelines. An agent skill from Luciole-Studio/Misaka-Agent.

    171 GitHub starsUsed in 2 repos~2.4k tokens
    Productivity & AutomationAuto-check: notes

More from NousResearch/hermes-agent

All 31 skills in this repo
  • AI Presenter Video

    NousResearch/hermes-agent

    Produces a presenter-led video from a topic or script plus one authorized presenter image, with captions, lip-sync checks and acceptance reports.

    253k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Word DOCX Toolkit

    NousResearch/hermes-agent

    Creates, reads, edits and templates Word .docx files with python-docx scripts, including tracked changes, comments, tables of contents and health checks.

    253k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Grounded Citations

    NousResearch/hermes-agent

    Attaches a numbered, URL-backed citation to every outside fact in an answer or document, rejecting quotes that aren't real.

    253k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • PDF

    NousResearch/hermes-agent

    PDF files: create, read, merge, fill, OCR, edit text. An agent skill from NousResearch/hermes-agent.

    253k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Scrollcraft

    NousResearch/hermes-agent

    Premium scroll-driven landing pages; scroll = timeline. An agent skill from NousResearch/hermes-agent.

    253k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • XLSX

    NousResearch/hermes-agent

    Create, read, edit Excel .xlsx workbooks and CSVs. An agent skill from NousResearch/hermes-agent.

    253k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Questions about Sdlc Review

What does Sdlc Review do?

Review Kanban handoffs and route verified outcomes. An agent skill from NousResearch/hermes-agent. Sdlc Review is an agent skill from NousResearch/hermes-agent. Review Kanban handoffs and route verified outcomes.

When should I use Sdlc Review?

Sdlc Review fits situations like: tasks that involve Task management.

How do I install Sdlc Review in Claude Code?

Run `npx skills add NousResearch/hermes-agent --skill sdlc-review -a claude-code`. Or copy the skill folder (skills/devops/sdlc-review in NousResearch/hermes-agent) into .claude/skills/sdlc-review in your project. Claude Code loads it when a task matches its description.

How do I install Sdlc Review in Codex?

Run `npx skills add NousResearch/hermes-agent --skill sdlc-review -a codex`. Or copy the skill folder (skills/devops/sdlc-review in NousResearch/hermes-agent) into .agents/skills/sdlc-review in your project. Codex loads it when a task matches its description.

Can I use Sdlc Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NousResearch/hermes-agent --skill sdlc-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdlc-review, .gemini/skills/sdlc-review, .github/skills/sdlc-review and .opencode/skills/sdlc-review in your project.

What does Sdlc Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Sdlc Review is instructions for the agent only.

Does Sdlc Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sdlc Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sdlc Review use?

Sdlc Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sdlc Review use?

About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sdlc Review?

Skills that share tags, products or a category with Sdlc Review: Superset Agent Standup (superset-sh/superset, 15k stars), AgentRQ Workspace Agent (agentrq/agentrq, 1.1k stars), Markdown Task Manager (ioniks/MarkdownTaskManager, 535 stars) and Pi Messenger Crew (nicobailon/pi-messenger, 719 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdlc Review?

NousResearch (a GitHub organization) maintains it in NousResearch/hermes-agent, which has 252,350 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 10, 2026.

Source: NousResearch/hermes-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.