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 agentmods add commands/blendsdk/claude-codeops/analyze_projectgit clone --depth 1 https://github.com/blendsdk/claude-codeopsWhat 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 | $0.00054 | $0.02730 |
| Opus 5 | $0.00027 | $0.01365 |
| Sonnet 5 | $0.00011 | $0.00546 |
| Haiku 4.5 | $0.00005 | $0.00273 |
Grade A, and why
analyze_project 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.
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.
analyze_project — generate/refresh this project's CLAUDE.md
Detect this project's toolchain and conventions and write them to a project-level CLAUDE.md
so every Claude Code session (and every CodeOps skill) adapts to this project. A non-flag
$ARGUMENTS value is the target root (otherwise the current working directory); the flags
--compact and --dry-run select the leaning mode described under Compact mode below.
This replaces the old CodeOps MCP analyze_project tool, which wrote .clinerules/project.md.
The Claude Code equivalent is the project's CLAUDE.md.
Step 1 — Detect (read-only)
Inspect manifests and structure. Look for and read whichever exist:
package.json, pnpm-workspace.yaml/turbo.json/nx.json (monorepo), tsconfig.json,
Cargo.toml, go.mod, pyproject.toml/setup.cfg/requirements.txt, composer.json,
Gemfile, pom.xml/build.gradle, docker-compose.yml/Dockerfile, Makefile,
CI configs under .github/workflows/, and the lockfile (to infer the package manager).
From these, determine: project name, type (web-app / api / library / cli / mobile / infrastructure / compiler / monorepo), language(s), framework(s), package manager, test framework, and the build / test / verify / clean commands. Map the top-level directory structure and where source vs. test files live. Detect whether it is a monorepo.
Use only facts you can verify from the files — never invent commands. If something can't be
determined, leave a clearly-marked TODO: placeholder.
Step 2 — Route by branch (parallel-worktree safety)
CLAUDE.md is one repo-wide file, so two agents refreshing it on different branches collide at
merge time. Its Toolchain / Commands / Project structure are derived from the tree and can
always be regenerated, so treat CLAUDE.md like a derived artifact: concentrate writes on one
branch. Skip this whole step and just write normally if git is unavailable.
Determine:
- current branch —
git rev-parse --abbrev-ref HEAD - integration branch —
integrationBranchfromcodeops/.codeops.ymlif present, else the repo default (git symbolic-ref refs/remotes/origin/HEAD, elsemain/master) - parallel? — whether
git worktree listshows more than one worktree
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.
- yesterday First seen · 199 lines · 54 tokens per session scan A 7b589d64eb5e
analyze_project is a command published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 2,730 once invoked, about $0.0003 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.