A guided procedure for carrying out one step of the TraceBug launch plan. It reads the current project status and plan, proposes small work steps, and reports what changed and was checked.

Use it to continue a numbered launch phase, make commit-sized changes, run the required checks, and produce a consistent progress report.

It prevents work from relying on outdated archive files or skipping approval and verification. It also makes unverified checks and human tasks visible.

How prashantsinghmangat/TraceBug-ai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to prashantsinghmangat/TraceBug-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/prashantsinghmangat/TraceBug-ai/main/.claude/skills/phase/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/prashantsinghmangat/TraceBug-ai

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/prashantsinghmangat/tracebug-ai/phase/github.svg)](https://agentmods.dev/skills/prashantsinghmangat/tracebug-ai/phase)

Your own site

<a href="https://agentmods.dev/skills/prashantsinghmangat/tracebug-ai/phase"><img src="https://agentmods.dev/badge/skills/prashantsinghmangat/tracebug-ai/phase/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/prashantsinghmangat/tracebug-ai/phase"><img src="https://agentmods.dev/badge/skills/prashantsinghmangat/tracebug-ai/phase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 621 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.00621
Opus 5.5	$0.00013	$0.00248
Sonnet 5.5	$0.00007	$0.00124
Haiku 4.5	$0.00003	$0.00062

Measured 4d ago against content hash 668494303081, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phase 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 4d 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.

.claude/skills/phase/SKILL.md · 40 lines

What it actually says

Read only these. docs/launch/STATE.md (where things stand, ~1 page) and the named phase's live section in docs/launch/PLAN.md. Read docs/launch/CODEMAP.md before searching the large files. Do not open PLAN-archive.md, PROGRESS-archive.md or phase0-findings-archive.md — they are closed history and much of what they say is no longer true. If you do need one to answer why a finished decision went that way, say so first.
Plan in <=10 bullets. Show it and wait for approval unless the user said "go".
Work in commit-sized steps. After each step run the gates skill, then STOP and report in this shape, nothing longer:
- Changed: files, one line each
- Verified: check.mjs summary lines, plus any e2e totals line
- Needs a human: bullets, or "nothing"
- Commit message: <=8 lines
Say what you could not verify. Anything needing a real Mac, a second browser, a store upload or a fresh profile is a row for docs/RELEASE_CHECKLIST.md, not a claim. Never report a manual check as passing.
Keep the map honest. If a CODEMAP.md entry is more than ~50 lines off, or a mapped function moved or was renamed, update CODEMAP.md in the same step.
After each step: rewrite docs/launch/STATE.md (replace, don't append — it is current state, not a log) and add <=5 lines to docs/launch/PROGRESS.md. If PROGRESS.md passes ~150 lines, move its oldest entries to PROGRESS-archive.md. Update CHANGELOG.md under 1.11.0 when the change is user-visible — and fix any existing entry the change makes false, rather than only adding to it.
Never commit, push, or add a manifest permission. Leave the work uncommitted on develop and suggest a message. Removing a permission or making one optional is fine.
If the plan is wrong, say so and keep going. Finished phases often invalidate a later phase's text (Phase 3 made Ctrl+Shift+B the wrong shortcut to document, Phase 2b resolved a Phase 6 item). Correct the instruction in PLAN.md as part of the step instead of following it, and note the correction in the report.

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.

4d ago First seen · 40 lines · 33 tokens per session scan A 668494303081

Subscribe to this mod's changes

phase is a skill published in the GitHub repository prashantsinghmangat/TraceBug-ai (4 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 621 once invoked, about $0.0001 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 2026-10-17.

Planning Project management

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.

Donchitos/Claude-Code-Game-Studios · 48 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

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…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

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,"…

petrkindlmann/qa-skills · 124 tokens

TraceBug-ai: Skill for Claude Code