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 skills add aiappsgbb/awesome-gbb --skill progress-guardgit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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.
[](https://agentmods.dev/skills/aiappsgbb/awesome-gbb/progress-guard)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/progress-guard"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/progress-guard/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.
<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/progress-guard"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/progress-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.01462 |
| Opus 5.5 | $0.00032 | $0.00585 |
| Sonnet 5.5 | $0.00016 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
progress-guard 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 19d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Progress guard
Execution memory and bounded recovery, not a planner, supervisor or tool watchdog. This skill grants no authority and installs no hooks, timers or background work.
Start small
Ordinary solo work stays direct; loading this skill never requires a child. Simple tasks need no ledger. For complex/stalled work, reuse the plan/todos and one existing snapshot; initialize from confirmed facts only if absent. Use storage.md for the store and optional fields. Do not delay useful work to perfect bookkeeping or create a competing plan.
If native discovery fails, read an accessible canonical SKILL.md once and record the failure, fallback path/version and owning runtime. File loading is not native discovery. Reuse that route after compaction. Retry native discovery only after a concrete runtime/catalog change. Children verify their own loading, not the parent's. Never route around a policy denial; if no permitted source is available, report the blocker.
Evidence, not activity
Progress is a verified deliverable increment, reproducible failure or observation that changes the next action. Reference its source/context; distinguish delivery from diagnostic learning and check that learning still advances the outcome. Plans, retries, pings, launches, bookkeeping and unchanged status are not progress. A passing component or child milestone is not usable end-to-end delivery.
Record only meaningful boundaries
Append one event with a complete compact snapshot at meaningful decisions, changed knowledge/failure, blocks, delivery, pause/handoff and uncertain external operation boundaries. Reuse native history for routine calls; keep logs/artifacts outside the ledger and store pointers, not transcripts or secrets.
Before long/risky operations, preserve intent, context and recovery lookup; retain the returned handle. After interruption, UNKNOWN is not failure: reconcile actual effects before retrying. Ledger writes and external effects are not atomic. A successful append receipt is sufficient; no compulsory full readback after every append. Read when recovery or uncertainty requires it, not as a ritual.
What ships with it
10 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.
- references/children.md 11 KB
- references/compaction.md 4.8 KB
- references/last_validated.yaml 1.5 KB
- references/ledger.sql 2.8 KB
- references/storage.md 11 KB
- scripts/ledger.py 10.0 KB runs code
- tests/scenarios.md 14 KB
- tests/test_handoff.py 33 KB runs code
- tests/test_ledger.py 13 KB runs code
- tests/test_roles.py 5.5 KB runs code
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.
- 19d ago Changed · -95 lines 63e789e7de23
- 20d ago Changed · +19 lines 61e30baa9511
- 23d ago Changed · +9 lines 5cbe30a61467
- 26d ago Changed · +13 lines 03c8d6fb6386
- 27d ago Changed · +33 lines · +4 tokens per session 82f3219903a7
- 28d ago First seen · 159 lines · 76 tokens per session scan A ff6bf52b0a42
progress-guard is a skill published in the GitHub repository aiappsgbb/awesome-gbb (8 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,462 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.