thread-close

A command for ending a research thread by either recording an evidence-based conclusion or marking it abandoned with a reason. A research thread is a tracked line of investigation.

In plain words
What is it for?
Use it after resolving a research thread or deciding that it is a dead end, including updating its experiments and conclusion document when needed.
Why use it?
It prevents unfinished research from being left in an unclear state and preserves why the work ended.

Command

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 commands/zhyx12/projtool/thread-close
Clone the repo
git clone --depth 1 https://github.com/zhyx12/projtool
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00041 $0.00710
Opus 5 $0.00020 $0.00355
Sonnet 5 $0.00008 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured yesterday against content hash 65ba17452a09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

thread-close 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 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.

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.

src/projtool/assets/project_templates/claude/commands/thread-close.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/thread-close — conclude or abandon a research thread

A thread ends one of two ways: concluded (it reached a verdict worth pinning) or abandoned (a dead end, closed with a reason). Ask which the user wants if it isn't clear. Never auto-close anything on their behalf.

If registry/ under the docs root is absent (paths.docs_dir in .proj-tool/project.toml, docs/ by default) there is nothing to close — the project predates the registry. Explain that and point at /thread-new (to start lineage now) or /migrate-docs (to adopt the old plans/ + exp/ layout first).

Conclude

  1. Resolve the thread with mcp__projtool__thread_tree. If the thread is paused, it cannot conclude directly — resume it first (thread_status(new_status="active")), then proceed. The registry now reflects run outcomes: launching/finalizing runs advances each experiment plannedrunningfinalized, so thread_tree shows real run counts and statuses. For a non-terminal experiment that will never run — a plan superseded before launch, or work folded into a sibling — close it explicitly with mcp__projtool__experiment_status(experiment=<slug|id>, new_status="finalized", no_run_note="…"), or new_status="abandoned" for a dead end. The run manifests (list_runs / compare_runs) remain the fine-grained truth about individual runs.
  2. Gather the evidence: findings.md, the tail of journal.md, mcp__projtool__compare_runs, and the relevant reports.
  3. Write threads/<slug>/conclusion.md citing pinned evidence: the run_ids that settle it, report paths, and headline metrics inline (so the verdict survives even if outputs are later deleted). Commit narrowly in the docs repo — git add only that file.
  4. Record the verdict. mcp__projtool__thread_status(thread=<slug>, new_status="concluded", conclusion_doc="threads/<slug>/conclusion.md"). The tool requires conclusion_doc to exist on disk — write it before the call.

Read the full file on GitHub · 53 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 · 53 lines · 41 tokens per session scan A 65ba17452a09

Subscribe to this mod's changes

thread-close is a command published in the GitHub repository zhyx12/projtool (1 stars, last pushed 18d ago), licensed MIT. It adds 41 tokens to every session and 710 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.