implementation-tracker
Skill8 starsChanged 6 months agoMITView on GitHub
Use when implementing large issues across multiple sessions. Creates and maintains a living progress document that tracks completed work, decisions, refinements, and findings.
In this repository129 other files it gives its agents.
- AGENTS.mdAGENTS.md
- guidance/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- guidance/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- blast-radius-checkSkill
- brainstormingSkill
- branch-flow-gateSkill
- branch-sync-gateSkill
- codebase-reconSkill
- codeowners-drift-auditSkill
- code-review-batterySkill
- cognitive-complexity-refactoringSkill
- debateSkill
- debug-conductorSkill
- dispatching-parallel-agentsSkill
- domain-buildSkill
- evidence-adjudicatorSkill
- executing-plansSkill
- external-cli-auditSkill
- feature-developmentSkill
- field-rename-verificationSkill
- finishing-a-development-branchSkill
- git-branch-conventionsSkill
- gitlab-cliSkill
- hotfix-charterSkill
- incident-revert-reviewSkill
- infra-config-investigatorSkill
- investigation-stateSkill
- kernel-splitSkill
- llm-behavior-investigatorSkill
- llm-skill-reviewSkill
- merge-authorization-gateSkill
- micro-harsh-reviewSkill
- output-verificationSkill
- pre-commit-gateSkill
- progressive-code-review-gateSkill
- progressive-harsh-reviewSkill
- providing-code-reviewSkill
- pr-triage-gateSkill
- push-authorization-gateSkill
- receiving-code-reviewSkill
- reproduction-experiment-investigatorSkill
- requesting-code-reviewSkill
- requirements-validation-pmSkill
- requirements-validationSkill
- scope-tripwireSkill
- session-handoffSkill
- skills-hierarchy-tuningSkill
- sp-bughuntSkill
- state-consistency-investigatorSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- timeline-trace-investigatorSkill
- token-estimationSkill
- unified-commit-gateSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
When existing progress doc found:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Implementation Tracker
Purpose: Maintain implementation context across sessions Path:
docs/plans/{PREFIX}-XXXX-progress.md(git-ignored during active work)
Announce at start: "Using implementation-tracker to maintain progress across sessions."
When to Use
- Implementing a large issue that will span multiple sessions
- Resuming work after a context break and needing to reload prior state
- Tracking decisions, refinements, and open questions during a multi-phase refactor
- Auditing completeness of a feature (what was planned vs. what was actually done)
Triggers
| Trigger | Action |
writing-plans completes | Auto-create progress doc |
| "Track implementation for {PREFIX}-XXX" | Manual creation |
| "Update progress" / milestone | Update doc + verify |
| "Resume work on {PREFIX}-XXX" | Load existing context |
| "Implementation complete" | Archive prompt |
Session Resume
When existing progress doc found:
I found: docs/plans/{PREFIX}-1234-progress.md
Last session: aug_abc123 (2026-03-05)
Status: 3/7 tasks, 2 decisions, 1 open question
[Yes / No / Show summary first]What Carries Forward
| Facts (persist) | Fresh Each Session |
| Completed tasks, files modified | Reasoning/approach |
| Blockers, decisions, refinements | Tool call sequences |
| Open questions, key insights | Error messages |
| Wiki context | Debugging hypotheses |
Verification (After Every Update)
| Order | Method | Purpose |
| 1 | git diff --name-only | What actually changed |
| 2 | test -f path/to/file.ts | Files exist |
| 3 | grep -rn "symbol" --include="*.ts" | Symbols present |
| 4 | tsc --noEmit | Type errors |
| 5 | npm test -- --filter=relevant | Tests pass |
Auto-Condense
Target: ~1,500 words. When exceeded: move completed tasks to summary table, condense session summaries, archive resolved questions.
Red Flags
- Progress doc says complete but git shows no changes
- Verification fails after update
- Doc >2,000 words without condensing
- Wiki context stale (>7 days)
Companion Skills
| Skill | Relationship |
writing-plans | Chains into this skill |
Failure Modes
| Mode | Symptom | Recovery |
| Scope drift | Tracking items not in original plan | Compare against plan regularly |
| False completion | Marking done without verifying behavior | Run verification after each update |
| Missing downstream | Tracking primary changes only | Check tests and docs too |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.