AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Aidlc Tracking

skill-indranildchandra-claude-local-starter-aidlc-tracking · by indranildchandra

AI Driven Development Lifecycle tracking — canonical formats for all project tracking files. Invoke before writing to any tracking file or before compaction.

No reviews yet
0 installs
39 views
0.0% view→install

Install

$ agentstack add skill-indranildchandra-claude-local-starter-aidlc-tracking

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-indranildchandra-claude-local-starter-aidlc-tracking)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Aidlc Tracking? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

AIDLC Tracking

When to invoke this skill

  • Before writing to any tracking file — load formats.md to get the exact template
  • Before running or suggesting /compact — write a pre-compact snapshot first
  • When auto-compaction is detected — immediately write a pre-compact snapshot to tasks/tracker.md
  • On /init-repo — use formats to scaffold all tracking files; also run npx gitnexus analyze

Tracking files and their purpose

| File | Purpose | Write rule | |------|---------|------------| | docs/plan.md | Architectural intent, before implementation | Append newest at TOP | | tasks/todo.md | Live execution tracking during a session | Rewrite as work evolves | | tasks/tracker.md | Append-only log of every task + session snapshot | Append newest at TOP | | audit/changelog.md | What changed in the codebase, after implementation | Append newest at TOP | | docs/design-review.md | Council review output from /design-review | Append newest at TOP | | tasks/lessons.md | Per-repo learning log, one entry per lesson learned | Append newest at TOP |

Core rules

  1. Never invent formats — always load formats.md from this skill before creating or appending to a tracking file
  2. All files are per-repo — never write tracking files to a global location
  3. Create on first use — if a tracking file doesn't exist, create it with the header from formats.md, then write the first entry below the header
  4. Prepend, never append — for all append-only files (tracker, plan, changelog, lessons, design-review): insert each new entry immediately after the file header so the newest entry is always at the top. Never write to the end of the file. Only todo.md is rewritten wholesale.
  5. Timestamps always use YYYY-MM-DD HH:MM:SS format

Pre-compact protocol

Before running /compact or when context auto-compaction is imminent:

  1. Invoke /log-context to write a pre-compact snapshot to tasks/tracker.md
  2. The snapshot must capture enough detail for a cold-start in the next session
  3. Then proceed with compaction

Gitnexus integration

  • On init-repo: run npx gitnexus analyze to build the initial code knowledge graph
  • After major refactoring sessions: re-run npx gitnexus analyze to refresh the graph
  • Use gitnexus context tools (ctx_search, impact analysis) before editing files in unfamiliar modules
  • The gitnexus graph supplements but does not replace reading CLAUDE.md files

Formats reference

Load only the format file you need — do not load all formats at once:

| Writing to | Load this file | |------------|---------------| | tasks/tracker.md | aidlc-tracking/formats/tracker.md | | tasks/todo.md | aidlc-tracking/formats/todo.md | | tasks/lessons.md | aidlc-tracking/formats/lessons.md | | docs/plan.md | aidlc-tracking/formats/plan.md | | audit/changelog.md | aidlc-tracking/formats/changelog.md | | docs/design-review.md | aidlc-tracking/formats/design-review.md |

formats.md is kept as a combined reference for humans — use the individual files above in code.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.