session-close

A session-closing workflow that finishes issue handling and produces a final report. It supports work done in a separate worktree as well as work done directly on a branch or the main path.

In plain words
What is it for?
Use it after a work session when a merged change needs issue closure, outcome collection, and a final report.
Why use it?
Closing a coding session can involve several final actions, such as confirming a merge and collecting the outcome. This tool coordinates those actions so the final report reflects what actually happened.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nirecom/agents/session-close
Any agent
npx skills add nirecom/agents --skill session-close
Clone the repo
git clone --depth 1 https://github.com/nirecom/agents

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,746 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.02746
Opus 5 $0.00025 $0.01373
Sonnet 5 $0.00010 $0.00549
Haiku 4.5 $0.00005 $0.00275

Measured yesterday against content hash e5e76205660a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-close scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `/issue-close-finalize` is invoked via the Skill tool only (never `bash`/`spawnSync`).
skills/session-close/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session close orchestrator. Drives issue-close-finalize (when applicable), collects the outcome JSON written by Step L, and emits the Final Report by substituting the skeleton from hooks/lib/final-report-schema.renderSkeleton. Replaces the legacy "Step 7" emit inside /worktree-end so the Final Report reflects every terminal action.

Pre-flight

  • AGENTS_CONFIG_DIR must be set.
  • Caller context (under ENFORCE_WORKTREE=on): /worktree-end Steps 1–6i have already completed (worktree merged and removed; <PLANS_DIR>/<session-id>-final-report-env.json exists).
  • Caller context (under ENFORCE_WORKTREE=off): the PR is merged. No worktree-end ran; the env file does not yet exist.

Step SC-0 — Resolve PLANS_DIR and session id

PLANS_DIR=$(bash "$AGENTS_CONFIG_DIR/bin/workflow-plans-dir" 2>/dev/null \
              || printf '%s\n' "${WORKFLOW_PLANS_DIR:-$HOME/.workflow-plans}")
printf 'PLANS_DIR=%s\n' "$PLANS_DIR"

Substitute the absolute path for <PLANS_DIR> in every subsequent step. Resolve <session-id> from $CLAUDE_ENV_FILE (CLAUDE_SESSION_ID) with the fallback chain used by --from-session. If unresolvable, abort: session id unresolved — cannot render Final Report.

<PLANS_DIR> and <session-id> are LLM-substituted literals — shell variables do not persist between Bash tool calls.

Step SC-1a — Detect WF-META session

Run: node "$AGENTS_CONFIG_DIR/bin/session-close-detect-wf-meta.js" ""

  • stdout yes → WF-META session. Record IS_WF_META=yes as an LLM-tracked state literal (not a shell variable — every Bash call is self-contained). Proceed to SC-2C.
  • stdout no → proceed to SC-1b (ENFORCE_WORKTREE detection).

Step SC-1b — Detect ENFORCE_WORKTREE mode

Check via Bash: bash -c 'cd "$AGENTS_CONFIG_DIR" && bash "$AGENTS_CONFIG_DIR/bin/confirm-off" ENFORCE_WORKTREE on'

  • stdout ON or ERROR → worktree path (SC-2A).
  • stdout OFF → branch/main path (SC-2B).

Step SC-2A — Worktree path: reuse existing env JSON

Read the full file on GitHub · 199 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.

  1. yesterday First seen · 199 lines · 50 tokens per session scan A e5e76205660a

Subscribe to this mod's changes

session-close is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 2,746 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens