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 skills/max0max/goal-driven/goal-progress-trackernpx skills add MAX0MAX/goal-driven --skill goal-progress-trackergit clone --depth 1 https://github.com/MAX0MAX/goal-drivenWhat 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 | $0.00043 | $0.01740 |
| Opus 5 | $0.00022 | $0.00870 |
| Sonnet 5 | $0.00009 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
goal-progress-tracker 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Progress Tracker
Overview
goal-progress-tracker is the paired runtime tracking skill for Goal Contracts.
Use it to maintain one recovery-oriented Markdown artifact: Goal Progress Log.
This skill does not define the goal, does not rewrite the Goal Contract, does not replace runtime verification, and does not continue into planning or execution. It records the current state of execution clearly enough that a human or later agent can inspect the work, understand what has already been tried, and continue from the right checkpoint. When a runtime or operator maintains handoff state for a Goal Contract, this tracker is the protocol for keeping that state current from the initial checkpoint onward rather than reconstructing it only after the work stops.
When To Use
Use this skill only when all of these are true:
- a Goal Contract already exists
- the Goal Contract has entered execution or is about to enter execution
- the runtime or operator must maintain a durable Markdown status and recovery artifact that stays current during execution
- current progress, attempted paths, evidence, blockers, or resume guidance are available
Do not use this skill to draft a Goal Contract from scratch, judge contract validity, prescribe execution strategy, or replace a plan or checklist system.
Post-hoc reconstruction after execution has already finished is a recovery fallback when no maintained log exists. It is not compliant primary workflow for a runtime or operator that elected to maintain tracker handoff state.
Required Input
Read the full tracking package before updating the log.
Tracking Package:
goal_contract:
Goal Contract:
goal: "<one-sentence end state>"
scope:
in_scope:
- "<required work>"
out_of_scope:
- "<excluded work>"
success_criteria:
- "<observable completion condition>"
evidence:
- criterion: "<criterion or group>"
proof:
- "<planned command, artifact, diff, or review gate>"
guardrails:
- "<constraint, escalation rule, or approval boundary>"
current_status: "on_track"
completed_steps:
- "<checkpoint-level completed work>"
in_flight_step: "<current focus>"
attempted_paths:
- path: "<approach tried>"
result: "<worked | failed | partial>"
evidence:
- "<command output, diff, observation, or review result>"
verified_evidence:
- criterion: "<success criterion or group>"
proof:
- "<actual evidence>"
active_blockers:
- "<blocking issue or none>"
resume_hint:
- "<where to continue from>"
existing_log: "<optional current Goal Progress Log markdown>"
verifier_verdict: "<optional Verifier Verdict>"
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 236 lines · 43 tokens per session scan A 4615af484514
goal-progress-tracker is a skill published in the GitHub repository MAX0MAX/goal-driven (5 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,740 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.
Other skills, from other repositories
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.