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 marlonvidal/tech-manager-os --skill tmr-project-impactgit clone --depth 1 https://github.com/marlonvidal/tech-manager-osWrote 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/marlonvidal/tech-manager-os/tmr-project-impact)<a href="https://agentmods.dev/skills/marlonvidal/tech-manager-os/tmr-project-impact"><img src="https://agentmods.dev/badge/skills/marlonvidal/tech-manager-os/tmr-project-impact/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/marlonvidal/tech-manager-os/tmr-project-impact"><img src="https://agentmods.dev/badge/skills/marlonvidal/tech-manager-os/tmr-project-impact.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 | $0.00030 | $0.02277 |
| Opus 5 | $0.00015 | $0.01138 |
| Sonnet 5 | $0.00006 | $0.00455 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
tmr-project-impact 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 6d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmr-project-impact
Detects changes in declared source-of-truth files within a project and produces a human-readable impact report with per-document suggestions. Nothing is applied automatically — you review and decide.
Usage
/tmr-project-impact— run against the project in the current working directory/tmr-project-impact <project-path>— run against a specific project (path relative to vault root)/tmr-project-impact deps— interactively createdeps.yamlfor the current project/tmr-project-impact <project-path> deps— interactively createdeps.yamlfor a specific project
The vault root is the git repository root. All relative paths in this skill are relative to the vault root unless stated otherwise.
EXECUTION
When invoked, check if the user passed the argument deps (in any position). If so, follow the CREATE-DEPS section. Otherwise, follow these steps in order: LOCATE, DETECT, ANALYZE, REPORT.
LOCATE
Step L1: Resolve the project path
If a <project-path> argument was given, use it as the project root (relative to vault root).
If no argument was given:
- Run
git rev-parse --show-toplevelto get the vault root - Run
pwdto get the current working directory - Compute the relative path from vault root to cwd — this is the project path
- If the relative path is
.or empty (you are at the vault root), ask:
Wait for the user's response and use it as the project path.No project path provided and you are at the vault root. Which project? (e.g., my-company/projects/ai-enablement):
Store as PROJECT_ROOT = <vault-root>/<project-path>.
Step L2: Find and load deps.yaml
Check if <PROJECT_ROOT>/deps.yaml exists.
If it does NOT exist: Print:
No deps.yaml found in <project-path>.
Options:
a) Create deps.yaml interactively → /tmr-project-impact <project-path> deps
b) Cancel
Wait for the user's response. If a, follow the CREATE-DEPS section. If b or anything else, exit.
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.
- 6d ago First seen · 309 lines · 30 tokens per session scan A 94c54fa35076
tmr-project-impact is a skill published in the GitHub repository marlonvidal/tech-manager-os (17 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 2,277 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.